Jan 27, 10:11 PM

Microsoft's CoRAG Boosts AI Reasoning by Over 10 Points on KILT Benchmark

Researchers from Microsoft have introduced a novel approach to Retrieval Augmented Generation (RAG) known as Chain-of-Retrieval Augmented Generation (CoRAG). This method enhances the ability of AI systems to retrieve and reason over relevant information step by step before generating final answers. CoRAG addresses the limitations of traditional RAG methods, which typically perform a single retrieval step before generating responses, by allowing dynamic query reformulation based on evolving states. The approach has shown over 10 points improvement in multi-hop question answering tasks, setting a new state-of-the-art performance on the KILT benchmark for knowledge-intensive tasks. The training of CoRAG involves rejection sampling to generate intermediate retrieval chains, augmenting existing RAG datasets.

#Microsoft #Retrieval Augmented Generation

Written with ChatGPT .

Sources

Additional media

Image #1 for story microsoft-s-corag-boosts-ai-reasoning-over-10-points-on-kilt-benchmark-ab887c4c

Image #2 for story microsoft-s-corag-boosts-ai-reasoning-over-10-points-on-kilt-benchmark-ab887c4c

Image #3 for story microsoft-s-corag-boosts-ai-reasoning-over-10-points-on-kilt-benchmark-ab887c4c

Image #4 for story microsoft-s-corag-boosts-ai-reasoning-over-10-points-on-kilt-benchmark-ab887c4c

Image #5 for story microsoft-s-corag-boosts-ai-reasoning-over-10-points-on-kilt-benchmark-ab887c4c

Image #6 for story microsoft-s-corag-boosts-ai-reasoning-over-10-points-on-kilt-benchmark-ab887c4c

Image #7 for story microsoft-s-corag-boosts-ai-reasoning-over-10-points-on-kilt-benchmark-ab887c4c