Search papers, labs, and topics across Lattice.
This paper identifies a systematic answerability gap in conversational retrieval systems, where passages that are topically relevant do not necessarily support the correct answer. To address this, the authors introduce CLEAR, a framework that utilizes entailment distillation to enhance retrieval by focusing on answerability rather than just topical relevance. Experiments demonstrate that CLEAR significantly improves top-ranked precision across multiple datasets, particularly in scenarios with high topical noise, showcasing its effectiveness in refining conversational retrieval outcomes.
Shifting the focus from topical relevance to answerability, CLEAR reveals that many conversational retrievers miss the mark by overlooking critical answer-supporting passages.
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.
