Conv-CoA: Open-domain Question Answering via Conversational Chain-of-Action with Hopfield Retriever

Zhenyu Pan, Haozheng Luo, Ruochen Feng, Manling Li, Han Liu

Keywords: question answering, information retrieval, modern hopfield network

TL;DR: A hopfield-based retriever augmented conversational question answering

Abstract: We present a Conversational Chain-of-Action (Conv-CoA) framework for Open-domain Conversational Question Answering (OCQA). Compared with literature, Conv-CoA addresses three major challenges: (i) unfaithful hallucination that is inconsistent with real-time or domain facts, (ii) weak reasoning performance in conversational scenarios, and (iii) unsatisfying performance in conversational information retrieval. Our key contribution is a dynamic reasoning-retrieval mechanism that extracts the intent of the question and decomposes it into a reasoning chain to be solved via systematic prompting, pre-designed actions, updating the Contextual Knowledge Set (CKS), and a novel Hopfield-based retriever. Methodologically, we propose a resource-efficient Hopfield retriever to enhance the efficiency and accuracy of conversational information retrieval within our actions. Additionally, we propose a conversational-multi-reference faith score (Conv-MRFS) to verify and resolve conflicts between retrieved knowledge and answers in conversations. Empirically, we conduct comparisons between our framework and 23 state-of-the-art methods across five different research directions and two public benchmarks. These comparisons demonstrate that our Conv-CoA outperforms other methods in both the accuracy and efficiency dimensions.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 8020