Problem
Research questions and friction points this paper is trying to address.
conversational retrieval
topical relevance
answerability
entailment
From Topical Relevance to Answerability: Entailment Distillation for Conversational Retrieval
🤖 AI Summary
本文针对对话检索中话题相关性与可回答性不匹配的问题，提出CLEAR框架，通过蕴含蒸馏和反向推理召回模块提升答案准确性。
📝 Abstract
Existing conversational retrievers commonly treat topical relevance as a proxy for answerability. However, a passage that closely matches the dialogue context is not necessarily the one that supports the correct answer. We identify this mismatch as a systematic answerability gap. To address this issue, we propose CLEAR, a framework that shifts conversational retrieval from topical relevance to answerability. The core of CLEAR is entailment distillation, which transfers answer-passage entailment supervision into a cross-encoder reranker so that the reranker discriminates answer-supporting passages from topical distractors at inference time, without requiring answers. CLEAR is complemented by a passage-centric abductive recall module that brings low-similarity yet answerable passages into the candidate pool by inferring answerable queries from passages with an LLM. Across TopiOCQA, QReCC, and out-of-domain TREC CAsT datasets, CLEAR consistently improves top-ranked precision over strong query-rewriting and dense-retrieval baselines, with the largest gains observed in conversations involving heavier topical noise. Moreover, applying our reranker on top of an LLM-driven query rewriter yields further gains.
Innovation
Methods, ideas, or system contributions that make the work stand out.
entailment distillation
cross-encoder reranker
abductive recall
🔎 Similar Papers
No similar papers found.
