2026· IEEE Transactions on Audio, Speech, and Language Processing· Vol 34, pp. 4718-4730· 0 citations· 56 references
TL;DR
RADAR is introduced, a novel feedback-driven framework that leverages the reasoning capabilities of Large Reasoning Models (LRMs) to generate and refine queries and introduces the Attribution-based Iterative Reasoning-Rewrite Refinement (AIR3) algorithm, which drives an iterative refinement process of pruning redundant reasoning and regenerating rewrites, ensuring the final query is aligned with retriever preferences.
Abstract
Conversational Query Rewriting (CQR) plays a vital role in modern information retrieval by transforming ambiguous user queries into self-contained versions that can be effectively processed by standard retrieval systems. Although essential for maintaining conversational context, current approaches tend to depend heavily on explicit dialogue history, leading to poor performance in situations where contextual information is limited or when topics shift abruptly. Consequently, the limited ability to look beyond explicit history hinders the generation of diverse and effective queries when historical cues are insufficient or misleading. To address these issues, we propose a design motivation grounded in dual-perspective reasoning. We posit that effective rewriting requires not only resolving historical dependencies but also proactively capturing the user's underlying search intent. Guided by these dual perspectives, we introduce RADAR, a novel feedback-driven framework that leverages the reasoning capabilities of Large Reasoning Models (LRMs) to generate and refine queries. Specifically, we design a two-stage framework. First, we construct an initial corpus of dual-perspective Chain-of-Thought (CoT) reasoning via In-Context Learning (ICL). However, generic reasoning paths can be noisy and retriever-agnostic. To bridge this gap, our second stage introduces the Attribution-based Iterative Reasoning-Rewrite Refinement (AIR3) algorithm. AIR3 leverages passage feedback to identify and quantify the fine-grained contribution of each token and sentence to the retrieval success. This attribution drives an iterative refinement process of pruning redundant reasoning and regenerating rewrites, ensuring the final query is aligned with retriever preferences. We evaluate RADAR on QReCC and TopiOCQA using both sparse and dense retrievers. Results show that it consistently improves various LRM backbones and achieves competitive performance across both retrieval settings, demonstrating the effectiveness of integrating intrinsic reasoning with extrinsic retrieval feedback.
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.· Conference on Empirical Meth...· 0 citations
This paper compares five query-generation configurations within a behavior-adaptive assistant using BM25 and SPLADE retrieval, and finds that the weighted configuration obtains the highest mean retrieval scores, but this retrieval advantage does not coincide with the highest conversational satisfaction scores.
S. Zerhoudi, Ivica Kostric, Jelena Mitrović· 0 citations
A zero-shot unified resolution– retrieval approach that contextualizes and expands query embeddings using the conversation history and without fine-tuning on conversational data, and which can even outperform supervised methods in improving conversational retrieval.
Passage reranking plays a crucial role in information retrieval by refining the ordering of candidate passages to better reflect relevance. Existing listwise LLM rerankers with Chain-of-Thought (CoT) reasoning can handle complex queries effectively, but they suffer from substantial redundancy and high latency due to sl...
Yang Zhang, Wen-Han Liu, Qian-Nan Zhu et al.· Proceedings of the 2026 Conf...· 0 citations
CogMem, a cognitive memory architecture based on the PEC$^2$F (Person-Event-Concept-Claim-Fact) graph schema, is introduced, a cognitive memory architecture based on the PEC$^2$F (Person-Event-Concept-Claim-Fact) graph schema that supports complementary contributions from epistemic separation, consolidation, and agenti...
Zi-Rui Liao, Zheng-Xian Wu, Zhuo Chen et al.· Proceedings of the 2026 Conf...· 0 citations
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.