Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
gabrielchua 
posted an update 26 days ago
Post
1198
Sharing my first paper!

==
Large Language Models (LLMs) are powerful, but they're prone to off-topic misuse, where users push them beyond their intended scope. Think harmful prompts, jailbreaks, and misuse. So how do we build better guardrails?

Traditional guardrails rely on curated examples or classifiers. The problem?
⚠️ High false-positive rates
⚠️ Poor adaptability to new misuse types
⚠️ Require real-world data, which is often unavailable during pre-production

Our method skips the need for real-world misuse examples. Instead, we:
1️⃣ Define the problem space qualitatively
2️⃣ Use an LLM to generate synthetic misuse prompts
3️⃣ Train and test guardrails on this dataset

We apply this to the off-topic prompt detection problem, and fine-tune simple bi- and cross-encoder classifiers that outperform heuristics based on cosine similarity or prompt engineering.

Additionally, framing the problem as prompt relevance allows these fine-tuned classifiers to generalise to other risk categories (e.g., jailbreak, toxic prompts).

Through this work, we also open-source our dataset (2M examples, ~50M+ tokens) and models.

paper: A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection (2411.12946)

artifacts: govtech/off-topic-guardrail-673838a62e4c661f248e81a4
In this post