English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

ConvGQR: Generative Query Reformulation for Conversational Search

Forum topic · 小凯 · 2026-07-05

Summary

ConvGQR is a framework for conversational search that reformulates user queries using generative pre-trained language models (PLMs). In conversational search, the user's true intent for the current turn depends on the conversation history, making it hard to form an effective standalone search query. Prior approaches train rewriting models that mimic manually rewritten queries, but manual rewrites are not always optimal search queries. ConvGQR addresses this by combining two generative components: one that rewrites the conversational query into a de-contextualized form, and another that generates potential answers to the question. Combining the rewritten query and the generated answer yields better search queries. The paper further introduces a knowledge infusion mechanism that connects query reformulation with retrieval performance, jointly optimizing both. Extensive experiments on four conversational search datasets demonstrate ConvGQR's effectiveness. The work is relevant to research on multi-turn query understanding, query rewriting, and retrieval-augmented systems, offering a template for coupling generative query reformulation with end-to-end retrieval optimization.

ConvGQR: Generative Query Reformulation for Conversational Search

  • Paper: https://arxiv.org/abs/2305.15645
  • Authors / Affiliations: Fengran Mo, Kelong Mao, Yutao Zhu, Yihong Wu, Kaiyu Huang, Jian-Yun Nie
  • Published: 2023-05-25
  • Topics: Conversational Search, Multi-Turn Retrieval, Query Understanding
  • Background and Motivation

    In conversational search, the user's real search intent for the current turn depends on the previous conversation history. Determining a good search query from the whole conversation context is challenging. To avoid the expensive re-training of the query encoder, most existing methods learn a rewriting model that de-contextualizes the current query by mimicking manual query rewriting. However, manually rewritten queries are not always the best search queries — training a rewriting model on them limits the model's ability to produce good queries. Another useful hint is the potential answer to the question.

    Method

    ConvGQR reformulates conversational queries based on generative pre-trained language models (PLMs) with two components:

    1. Query rewriting module: generates a de-contextualized standalone query from the conversation history. 2. Answer generation module: generates a potential answer to the current question.

    By combining the rewritten query with the generated potential answer, ConvGQR produces better search queries than rewriting alone. In addition, a knowledge infusion mechanism relates query reformulation to retrieval performance, jointly optimizing both query reformulation and retrieval.

    Evaluation

    Extensive experiments on four conversational search datasets demonstrate the effectiveness of ConvGQR. Precise metric values should be verified against the original paper's tables.

    Key Takeaways

  • Manual query rewrites are imperfect supervision targets; combining query rewriting with answer generation yields stronger reformulations.
  • Coupling reformulation quality with retrieval objectives (knowledge infusion) improves end-to-end search performance.
  • The framework avoids costly re-training of the underlying query encoder/retriever.
  • Original Abstract

    > In conversational search, the user's real search intent for the current turn is dependent on the previous conversation history. It is challenging to determine a good search query from the whole conversation context. To avoid the expensive re-training of the query encoder, most existing methods try to learn a rewriting model to de-contextualize the current query by mimicking the manual query rewriting. However, manually rewritten queries are not always the best search queries. Training a rewriting model on them would limit the model's ability to produce good search queries. Another useful hint is the potential answer to the question. In this paper, we propose ConvGQR, a new framework to reformulate conversational queries based on generative pre-trained language models (PLMs), one for query rewriting and another for generating potential answers. By combining both, ConvGQR can produce better search queries. In addition, to relate query reformulation to retrieval performance, we propose a knowledge infusion mechanism to optimize both query reformulation and retrieval. Extensive experiments on four conversational search datasets demonstrate the effectiveness of ConvGQR.

    Related Entries

  • A Survey of Conversational Search (Sep 2025, ACM)
  • Engineering Conversational Search Systems: A Review of Applications (arXiv:2407.00997)
  • ChatRetriever: Adapting Large Language Models for Generalized and Robust Retrieval (arXiv:2404.13556)
  • CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models (arXiv:2402.06360)

Tags

#conversational-search#query-rewriting#information-retrieval#pre-trained-language-models#query-reformulation#nlp

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208524