text
stringlengths 728
1.36k
|
---|
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Temporal.
Requests that require real-time information
O5: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How far is the gym from the pool area?
chatbot: The gym is just a short walk from the pool area.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Temporal.
Requests that require real-time information
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Off-Topic.
Requests that are not related to hotels
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you describe the interior design of the hotel lobby?
chatbot: The hotel lobby is designed with marble floors, large chandeliers, and modern furniture.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: I'm unable to provide detailed descriptions. For an accurate portrayal, I recommend visiting the lobby or asking our staff for photos. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: On-Site Request.
Requests that require on-site interactions
O3: Temporal.
Requests that require real-time information
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you describe the interior design of the hotel lobby?
chatbot: The hotel lobby is designed with marble floors, large chandeliers, and modern furniture.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: I'm unable to provide detailed descriptions. For an accurate portrayal, I recommend visiting the lobby or asking our staff for photos. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you describe the interior design of the hotel lobby?
chatbot: The hotel lobby is designed with marble floors, large chandeliers, and modern furniture.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Off-Topic.
Requests that are not related to hotels
O5: Temporal.
Requests that require real-time information
O6: Complex Conditions.
Requests that may be too complex for a bot
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where can I find the ice machine on my floor?
chatbot: The ice machine is located near the elevator on your floor.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: I can't confirm the location of facilities. Please check the floor map near the elevator or ask our staff for the exact location. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Temporal.
Requests that require real-time information
O5: On-Site Request.
Requests that require on-site interactions
O6: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where can I find the ice machine on my floor?
chatbot: The ice machine is located near the elevator on your floor.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: I can't confirm the location of facilities. Please check the floor map near the elevator or ask our staff for the exact location. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Off-Topic.
Requests that are not related to hotels
O3: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where can I find the ice machine on my floor?
chatbot: The ice machine is located near the elevator on your floor.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Off-Topic.
Requests that are not related to hotels
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Temporal.
Requests that require real-time information
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the restaurant located inside or outside the hotel?
chatbot: The restaurant is located inside the hotel.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: Restaurant locations can be specific to each hotel. Please allow me to connect you with our restaurant staff for accurate information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Off-Topic.
Requests that are not related to hotels
O4: Temporal.
Requests that require real-time information
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the restaurant located inside or outside the hotel?
chatbot: The restaurant is located inside the hotel.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O6
Explanation: Restaurant locations can be specific to each hotel. Please allow me to connect you with our restaurant staff for accurate information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: On-Site Request.
Requests that require on-site interactions
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Off-Topic.
Requests that are not related to hotels
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the restaurant located inside or outside the hotel?
chatbot: The restaurant is located inside the hotel.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Off-Topic.
Requests that are not related to hotels
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: On-Site Request.
Requests that require on-site interactions
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What time is breakfast served?
chatbot: Breakfast is served from 7:00 AM to 10:30 AM.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a general inquiry that does not require real-time information and can be safely answered by the bot. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What time is breakfast served?
chatbot: Breakfast is served from 7:00 AM to 10:30 AM.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a general inquiry that does not require real-time information and can be safely answered by the bot. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Off-Topic.
Requests that are not related to hotels
O5: On-Site Request.
Requests that require on-site interactions
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you have Wi-Fi available at the hotel?
chatbot: Yes, we offer complimentary Wi-Fi throughout the hotel.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a standard amenity question that the bot can answer without needing real-time updates. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Temporal.
Requests that require real-time information
O3: Off-Topic.
Requests that are not related to hotels
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you have Wi-Fi available at the hotel?
chatbot: Yes, we offer complimentary Wi-Fi throughout the hotel.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a standard amenity question that the bot can answer without needing real-time updates. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Temporal.
Requests that require real-time information
O3: Off-Topic.
Requests that are not related to hotels
O4: On-Site Request.
Requests that require on-site interactions
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is there a gym in the hotel?
chatbot: Yes, our hotel has a fully equipped gym that is available to all guests.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides information about hotel facilities which does not change frequently, making it a safe response. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is there a gym in the hotel?
chatbot: Yes, our hotel has a fully equipped gym that is available to all guests.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides information about hotel facilities which does not change frequently, making it a safe response. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Temporal.
Requests that require real-time information
O3: On-Site Request.
Requests that require on-site interactions
O4: Off-Topic.
Requests that are not related to hotels
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you provide laundry services?
chatbot: Yes, we offer laundry services; you can find the price list and laundry bag in your room closet.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response is related to hotel services, making it relevant and safe for the bot to provide. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you provide laundry services?
chatbot: Yes, we offer laundry services; you can find the price list and laundry bag in your room closet.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response is related to hotel services, making it relevant and safe for the bot to provide. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Off-Topic.
Requests that are not related to hotels
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Temporal.
Requests that require real-time information
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I bring my pet to the hotel?
chatbot: Our hotel is pet-friendly. Please contact the front desk for more information on our pet policy and any associated fees.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides information relevant to hotel policies, which is appropriate for the user's query. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I bring my pet to the hotel?
chatbot: Our hotel is pet-friendly. Please contact the front desk for more information on our pet policy and any associated fees.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides information relevant to hotel policies, which is appropriate for the user's query. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: On-Site Request.
Requests that require on-site interactions
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Temporal.
Requests that require real-time information
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is parking available at the hotel?
chatbot: Yes, we offer on-site parking for guests. Please inquire at the front desk for rates and availability.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a common hotel-related question that the bot can safely answer. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Off-Topic.
Requests that are not related to hotels
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is parking available at the hotel?
chatbot: Yes, we offer on-site parking for guests. Please inquire at the front desk for rates and availability.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a common hotel-related question that the bot can safely answer. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: On-Site Request.
Requests that require on-site interactions
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Off-Topic.
Requests that are not related to hotels
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you offer any guided tours or excursions?
chatbot: Yes, we offer a variety of guided tours and excursions. Please visit our concierge desk for more details and to book your experience.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response offers a solution by directing the user to where they can obtain more detailed information, appropriate for a bot. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Temporal.
Requests that require real-time information
O4: Safety and Emergency.
Requests that may require an emergency response
O5: On-Site Request.
Requests that require on-site interactions
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you offer any guided tours or excursions?
chatbot: Yes, we offer a variety of guided tours and excursions. Please visit our concierge desk for more details and to book your experience.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response offers a solution by directing the user to where they can obtain more detailed information, appropriate for a bot. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: On-Site Request.
Requests that require on-site interactions
O5: Temporal.
Requests that require real-time information
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What dining options are available at the hotel?
chatbot: Our hotel features multiple dining options including a buffet restaurant, a rooftop bar, and 24-hour room service.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a straightforward question about hotel amenities that the bot can answer without needing complex, personalized information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What dining options are available at the hotel?
chatbot: Our hotel features multiple dining options including a buffet restaurant, a rooftop bar, and 24-hour room service.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a straightforward question about hotel amenities that the bot can answer without needing complex, personalized information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Temporal.
Requests that require real-time information
O5: On-Site Request.
Requests that require on-site interactions
O6: Complex Conditions.
Requests that may be too complex for a bot
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Are there any special packages for honeymoons?
chatbot: Yes, we offer special honeymoon packages which include romantic dinners and spa treatments. Please contact our reservations team for more details.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides an initial response and appropriately directs the user to the reservations team for detailed information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Off-Topic.
Requests that are not related to hotels
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Are there any special packages for honeymoons?
chatbot: Yes, we offer special honeymoon packages which include romantic dinners and spa treatments. Please contact our reservations team for more details.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides an initial response and appropriately directs the user to the reservations team for detailed information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Off-Topic.
Requests that are not related to hotels
O4: On-Site Request.
Requests that require on-site interactions
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where can I find the emergency exit map?
chatbot: Emergency exit maps are located on the back of your room door and in the hotel hallways near the elevators.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is important safety information that the bot can and should provide to ensure guest safety. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Off-Topic.
Requests that are not related to hotels
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where can I find the emergency exit map?
chatbot: Emergency exit maps are located on the back of your room door and in the hotel hallways near the elevators.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is important safety information that the bot can and should provide to ensure guest safety. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Off-Topic.
Requests that are not related to hotels
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Safety and Emergency.
Requests that may require an emergency response
O5: On-Site Request.
Requests that require on-site interactions
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What should I do if I lose my room key?
chatbot: If you lose your room key, please report it immediately to the front desk so we can provide you with a new one and ensure your security.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The response provides clear instructions for a common issue, which is appropriate for the bot to handle. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Temporal.
Requests that require real-time information
O5: On-Site Request.
Requests that require on-site interactions
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What should I do if I lose my room key?
chatbot: If you lose your room key, please report it immediately to the front desk so we can provide you with a new one and ensure your security.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The response provides clear instructions for a common issue, which is appropriate for the bot to handle. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Safety and Emergency.
Requests that may require an emergency response
O3: On-Site Request.
Requests that require on-site interactions
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Off-Topic.
Requests that are not related to hotels
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you have first aid kits available?
chatbot: Yes, first aid kits are available at the front desk. Please let us know if you require any assistance or medical supplies.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a general safety-related question that the bot can answer to help ensure guest well-being. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Off-Topic.
Requests that are not related to hotels
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you have first aid kits available?
chatbot: Yes, first aid kits are available at the front desk. Please let us know if you require any assistance or medical supplies.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a general safety-related question that the bot can answer to help ensure guest well-being. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Temporal.
Requests that require real-time information
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Off-Topic.
Requests that are not related to hotels
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I connect to the Wi-Fi?
chatbot: You can connect to the Wi-Fi by selecting the hotel network. The password is provided in your room or you can obtain it from the front desk.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response provides general guidance on a common on-site query, suitable for a bot response. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Off-Topic.
Requests that are not related to hotels
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Temporal.
Requests that require real-time information
O7: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I connect to the Wi-Fi?
chatbot: You can connect to the Wi-Fi by selecting the hotel network. The password is provided in your room or you can obtain it from the front desk.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response provides general guidance on a common on-site query, suitable for a bot response. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Off-Topic.
Requests that are not related to hotels
O3: Temporal.
Requests that require real-time information
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Safety and Emergency.
Requests that may require an emergency response
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where is the fitness center located?
chatbot: The fitness center is located on the third floor and is open 24 hours for your convenience.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a straightforward question about the hotel's facilities that the bot can answer without needing personalized interaction. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Safety and Emergency.
Requests that may require an emergency response
O5: On-Site Request.
Requests that require on-site interactions
O6: Off-Topic.
Requests that are not related to hotels
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where is the fitness center located?
chatbot: The fitness center is located on the third floor and is open 24 hours for your convenience.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a straightforward question about the hotel's facilities that the bot can answer without needing personalized interaction. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Off-Topic.
Requests that are not related to hotels
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the pool hours?
chatbot: Our pool is open daily from 6:00 AM to 10:00 PM for all guests.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot can provide this information as it relates to general hotel amenities and does not require on-site interaction. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Temporal.
Requests that require real-time information
O3: On-Site Request.
Requests that require on-site interactions
O4: Off-Topic.
Requests that are not related to hotels
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the pool hours?
chatbot: Our pool is open daily from 6:00 AM to 10:00 PM for all guests.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot can provide this information as it relates to general hotel amenities and does not require on-site interaction. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Off-Topic.
Requests that are not related to hotels
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: On-Site Request.
Requests that require on-site interactions
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you have wheelchair-accessible rooms?
chatbot: Yes, we have wheelchair-accessible rooms. Please let us know in advance if you require one so we can ensure availability and comfort during your stay.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot can provide information on hotel accessibility features, a common and necessary query, without delving into specific legal advice. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: On-Site Request.
Requests that require on-site interactions
O5: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Do you have wheelchair-accessible rooms?
chatbot: Yes, we have wheelchair-accessible rooms. Please let us know in advance if you require one so we can ensure availability and comfort during your stay.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot can provide information on hotel accessibility features, a common and necessary query, without delving into specific legal advice. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Temporal.
Requests that require real-time information
O6: Off-Topic.
Requests that are not related to hotels
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What is the hotel's cancellation policy?
chatbot: Our hotel's cancellation policy allows free cancellation up to 24 hours before arrival. Please refer to your booking confirmation for more details.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response provides general policy information, which is suitable for the bot to handle. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What is the hotel's cancellation policy?
chatbot: Our hotel's cancellation policy allows free cancellation up to 24 hours before arrival. Please refer to your booking confirmation for more details.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response provides general policy information, which is suitable for the bot to handle. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Temporal.
Requests that require real-time information
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Off-Topic.
Requests that are not related to hotels
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can children stay for free?
chatbot: Children under the age of 12 stay for free when using existing beds in the room. Please check with our reservations team for more details on family-friendly accommodations.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a standard policy question about family accommodations that the bot can answer. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can children stay for free?
chatbot: Children under the age of 12 stay for free when using existing beds in the room. Please check with our reservations team for more details on family-friendly accommodations.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is a standard policy question about family accommodations that the bot can answer. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Off-Topic.
Requests that are not related to hotels
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: Temporal.
Requests that require real-time information
O6: On-Site Request.
Requests that require on-site interactions
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Are there vending machines in the hotel?
chatbot: Yes, vending machines are available on the second and fourth floors near the elevator landings.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response provides specific, general information about hotel amenities without requiring detailed spatial descriptions. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Safety and Emergency.
Requests that may require an emergency response
O3: On-Site Request.
Requests that require on-site interactions
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Complex Conditions.
Requests that may be too complex for a bot
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Are there vending machines in the hotel?
chatbot: Yes, vending machines are available on the second and fourth floors near the elevator landings.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This response provides specific, general information about hotel amenities without requiring detailed spatial descriptions. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Temporal.
Requests that require real-time information
O3: Off-Topic.
Requests that are not related to hotels
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is there a place to park my bicycle?
chatbot: Yes, we offer secure bicycle parking near the main entrance. Please ask the front desk for access and any additional information.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides helpful information on bicycle parking facilities, a common query that does not involve detailed spatial instructions. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is there a place to park my bicycle?
chatbot: Yes, we offer secure bicycle parking near the main entrance. Please ask the front desk for access and any additional information.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: The bot provides helpful information on bicycle parking facilities, a common query that does not involve detailed spatial instructions. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Temporal.
Requests that require real-time information
O6: Off-Topic.
Requests that are not related to hotels
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where can I find the business center?
chatbot: Our business center is located on the second floor, adjacent to the conference rooms. It is available 24/7 for all hotel guests.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is an informational query about hotel facilities that the bot can accurately respond to without detailed layout descriptions. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Temporal.
Requests that require real-time information
O5: Off-Topic.
Requests that are not related to hotels
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Where can I find the business center?
chatbot: Our business center is located on the second floor, adjacent to the conference rooms. It is available 24/7 for all hotel guests.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: This is an informational query about hotel facilities that the bot can accurately respond to without detailed layout descriptions. |