Skip to content

Breaking the Reference Bottleneck via Learning to Rewrite Conversational Queries without Gold Reference Passages

· 0 citations · 74 references

TL;DR

A novel reference-free preference optimization framework D UAL R EFORM that generates pseudo reference passages from commonly-encountered conversational datasets containing only queries and responses that achieves 96.9–99.1% of the retrieval accuracy attainable only with reference passages.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

CompCQR: Compositional Query Generation for Training-Free Conversational Search

This work proposes a novel training-free method that generates a very large number of queries with minimal LLM usage by compositionally combining a small set of atomic components and applies LLM reasoning to construct a high-quality document set that balances precision and recall while capturing the user's core intent.

Yunah Jang, Kang-il Lee, Joongbo Shin et al. · 0 citations
Preprint Oct 2026

Learning Multi-Step Query Rewriting via Corpus Feedback for Conversational Search

Conversational Query Rewriting (CQR) turns a context dependent user turn into a standalone query for a retriever, and most methods do this in a single step from the dialogue history before retrieving once. The rewrite is therefore fixed before any corpus evidence is available to correct its reference resolution or its...

João Coelho, Hong Wang, Jie Yuan et al. · 0 citations
Preprint Sep 2026

From Topical Relevance to Answerability: Entailment Distillation for Conversational Retrieval

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.

Shuai Qin, Guo-Jia An, Wei-Kang Guo et al. · 0 citations
#natural language process... Preprint Sep 2026

Grounding Memory Summarization in Utility Intent

This work proposes MemSuit, a self-distillation framework in which a teacher summarizer, conditioned on observed query-answer pairs, produces utility-aware memory entries that a student learns to reproduce from the raw conversation alone, confirming the value of grounding memory in downstream utility.

Zhen-Yu Lei, Ming-Jia Shi, Xing-Bo Fu et al. · 0 citations
Preprint Aug 2026

MemUse: Moving Memory Evaluation from Direct QA to Natural Integration in Long-Term Human-AI Conversation

It is hypothesize that existing benchmarks and user satisfaction are tracking different capabilities: benchmarks measure elicited retrieval (recall when asked), while conversation requires natural integration (detecting relevance and naturally weaving prior context into a response).

Ryuichi Sumida, K. Inoue, Tatsuya Kawahara · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.