A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry

TL;DR

This paper introduces AMD, a multi-agent dialogic framework for query expansion in IR, which uses Socratic questioning, answer generation, and feedback to create richer, more diverse query representations, outperforming existing methods.

Contribution

The paper presents a novel multi-agent dialogic approach for query expansion that enhances diversity and relevance in IR, leveraging inquiry and feedback mechanisms.

Findings

Outperforms previous query expansion methods on BEIR and TREC benchmarks.

Creates richer, more diverse query representations through multi-agent inquiry.

Demonstrates improved retrieval effectiveness in experimental evaluations.

Abstract

Query expansion is widely used in Information Retrieval (IR) to improve search outcomes by supplementing initial queries with richer information. While recent Large Language Model (LLM) based methods generate pseudo-relevant content and expanded terms via multiple prompts, they often yield homogeneous, narrow expansions that lack the diverse context needed to retrieve relevant information. In this paper, we propose AMD: a new Agent-Mediated Dialogic Framework that engages in a dialogic inquiry involving three specialized roles: (1) a Socratic Questioning Agent reformulates the initial query into three sub-questions, with each question inspired by a specific Socratic questioning dimension, including clarification, assumption probing, and implication probing, (2) a Dialogic Answering Agent generates pseudo-answers, enriching the query representation with multiple perspectives aligned to the user's intent, and (3) a Reflective Feedback Agent evaluates and refines these pseudo-answers, ensuring that only the most relevant and informative content is retained. By leveraging a multi-agent process, AMD effectively crafts richer query representations through inquiry and feedback refinement. Extensive experiments on benchmarks including BEIR and TREC demonstrate that our framework outperforms previous methods, offering a robust solution for retrieval tasks.