Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study
Researchers have developed ThinkGR, a novel framework that integrates Chain-of-Thought (CoT) reasoning into generative retrieval systems. This approach allows for iterative thinking and document identification within a single generative process, addressing limitations in handling complex, multi-step queries. ThinkGR employs a hybrid decoding strategy and a two-phase training method to bridge free-form thought generation with structured retrieval targets. Experiments show ThinkGR achieves state-of-the-art results on four multi-hop retrieval benchmarks, with an average performance improvement of 6.86%. AI
IMPACT Enhances retrieval systems for complex queries, potentially improving search accuracy in knowledge-intensive domains.