Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers

Youmin Ko, Sung Jong Seo, Hyunjoon Kim

Keywords: retieval-augmented generation, RAG, multi-hop question answering, contrasting layers, question augmentation

TL;DR: We propose a novel RAG framework in which a retriever and an LLM cooperate to exchange knowledge, and the retriever utilizes information of both earlier and later layers to accurately rank documents relevant to a question.

Abstract: Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downside of harnessing only LLMs. However, existing RAG methods for simple and multi-hop question answering (QA) are still prone to incorrect retrievals and hallucinations. To address these limitations, we propose CoopRAG, a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other by exchanging informative knowledge, and the earlier and later layers of the retriever model work cooperatively with each other to accurately rank the retrieved documents relevant to a given query. In this framework, we (i) unroll a question into sub-questions and a reasoning chain in which uncertain positions are masked, (ii) retrieve the documents relevant to the question augmented with the sub-questions and the reasoning chain, (iii) rerank the documents by contrasting layers of the retriever, and (iv) reconstruct the reasoning chain by filling the masked positions via the LLM. Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset in terms of both the retrieval and QA performances. Our code is available.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 27544