GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering
Paper
ā¢
2409.06595
ā¢
Published
ā¢
37
EVEIL
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
eveil-multimodal's activity
gautierviaudĀ
authored
a
paper
4 months ago
antonioloisonĀ
authored
a
paper
4 months ago
Post
735
ColPali: A new approach to efficient and intelligent document retrieval š
Our latest research paper, "ColPali: Efficient Document Retrieval with Vision Language Models," introduces a groundbreaking approach to large-scale visual document analysis. By leveraging Vision Language Models (VLMs), we have created a new framework for document retrieval that's both powerful and efficient.
Key Insights:
š” ColPali combines ColBERT's multi-vector strategy with VLMs' document understanding capabilities
āļø ColPali is based on PaliGemma-3B (SigLIP, Gemma-2B) + a linear projection layer and is trained to maximize the similarity between the document and the query embeddings
š The Vision Document Retrieval benchmark (ViDoRe) is a challenging dataset that spans various industry topics and aims at matching real-life retrieval scenarios
š ColPali outperforms existing models on all datasets in ViDoRe (average NDCG@5 of 81.3% vs 67.0% for the best baseline model)
ā” ColPali is faster at document embedding compared to traditional PDF parser pipelines, making ColPali viable for industrial use
š ColPali is highly interpretable thanks to patch-based similarity maps
Dive deeper into ColPali and explore our resources:
š Full paper: arxiv.org/abs/2407.01449
š ļø Datasets, model weights, evaluation code, leaderboard, demos: huggingface.co/vidore
Shoutout to my amazing co-authors Manuel Faysse ( @manu ) and Hugues Sibille ( @HugSib ). We are grateful for the invaluable feedback from Bilel Omrani, Gautier Viaud, Celine Hudelot, and Pierre Colombo. This work is sponsored by ILLUIN Technology. āØ
Our latest research paper, "ColPali: Efficient Document Retrieval with Vision Language Models," introduces a groundbreaking approach to large-scale visual document analysis. By leveraging Vision Language Models (VLMs), we have created a new framework for document retrieval that's both powerful and efficient.
Key Insights:
š” ColPali combines ColBERT's multi-vector strategy with VLMs' document understanding capabilities
āļø ColPali is based on PaliGemma-3B (SigLIP, Gemma-2B) + a linear projection layer and is trained to maximize the similarity between the document and the query embeddings
š The Vision Document Retrieval benchmark (ViDoRe) is a challenging dataset that spans various industry topics and aims at matching real-life retrieval scenarios
š ColPali outperforms existing models on all datasets in ViDoRe (average NDCG@5 of 81.3% vs 67.0% for the best baseline model)
ā” ColPali is faster at document embedding compared to traditional PDF parser pipelines, making ColPali viable for industrial use
š ColPali is highly interpretable thanks to patch-based similarity maps
Dive deeper into ColPali and explore our resources:
š Full paper: arxiv.org/abs/2407.01449
š ļø Datasets, model weights, evaluation code, leaderboard, demos: huggingface.co/vidore
Shoutout to my amazing co-authors Manuel Faysse ( @manu ) and Hugues Sibille ( @HugSib ). We are grateful for the invaluable feedback from Bilel Omrani, Gautier Viaud, Celine Hudelot, and Pierre Colombo. This work is sponsored by ILLUIN Technology. āØ
HugSibĀ
authored
a
paper
6 months ago
tonywu71Ā
authored
a
paper
6 months ago
gautierviaudĀ
authored
a
paper
11 months ago
jtourilleĀ
authored
a
paper
over 1 year ago