RAC: Retrieval-Augmented Clarification for Faithful Conversational Search

TL;DR

This paper presents RAC, a retrieval-augmented framework for generating clarification questions in conversational search that are grounded in the underlying corpus, improving faithfulness and relevance.

Contribution

RAC introduces a retrieval-augmented approach with contrastive optimization to generate corpus-faithful clarification questions, a novel focus in conversational search.

Findings

Significant improvements over baselines on four benchmarks.

Enhanced faithfulness of questions as measured by novel NLI and data-to-text metrics.

Effective use of retrieval strategies and contrastive training for grounded question generation.

Abstract

Clarification questions help conversational search systems resolve ambiguous or underspecified user queries. While prior work has focused on fluency and alignment with user intent, especially through facet extraction, much less attention has been paid to grounding clarifications in the underlying corpus. Without such grounding, systems risk asking questions that cannot be answered from the available documents. We introduce RAC (Retrieval-Augmented Clarification), a framework for generating corpus-faithful clarification questions. After comparing several indexing strategies for retrieval, we fine-tune a large language model to make optimal use of research context and to encourage the generation of evidence-based question. We then apply contrastive preference optimization to favor questions supported by retrieved passages over ungrounded alternatives. Evaluated on four benchmarks, RAC demonstrate significant improvements over baselines. In addition to LLM-as-Judge assessments, we introduce novel metrics derived from NLI and data-to-text to assess how well questions are anchored in the context, and we demonstrate that our approach consistently enhances faithfulness.