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

HAConvDR: History-Aware Conversational Dense Retrieval

Forum topic · 小凯 · 2026-07-05

Summary

HAConvDR (History-Aware Conversational Dense Retrieval) is a research paper by Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu, Zhan Su, Kaiyu Huang and colleagues, published on arXiv (2401.16659) in January 2024. Conversational search supports complex information retrieval through multi-turn interactions, requiring the system to reformulate search queries that incorporate relevant information from previous conversation turns. Existing conversational dense retrieval approaches typically fine-tune a pre-trained ad-hoc retriever on entire conversation sessions, which are often lengthy and noisy, and they are constrained by limited manual supervision signals in available datasets. HAConvDR addresses these issues with two key ideas: context-denoised query reformulation, and automatic mining of supervision signals based on the actual impact of historical turns. Experiments on two public conversational search datasets show improved history modeling capability, especially for long conversations involving topic shifts. The paper is relevant to research on conversational search, dense retrieval, and retrieval-augmented generation systems.

HAConvDR: History-Aware Conversational Dense Retrieval

Overview

  • Paper: History-Aware Conversational Dense Retrieval
  • Authors: Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu, Zhan Su, Kaiyu Huang, et al. (7 authors)
  • Published: 2024-01-30
  • Source: https://arxiv.org/abs/2401.16659
  • Category: Conversational Search
  • Problem Statement

    Conversational search facilitates complex information retrieval by enabling multi-turn interactions between users and the system. Supporting such interactions requires a comprehensive understanding of the conversational inputs to formulate a good search query based on historical information. In particular, the search query should include the relevant information from the previous conversation turns.

    However, current approaches for conversational dense retrieval primarily rely on fine-tuning a pre-trained ad-hoc retriever using the whole conversational search session, which can be lengthy and noisy. Moreover, existing approaches are limited by the amount of manual supervision signals in the existing datasets.

    Proposed Approach

    The authors propose HAConvDR, a History-Aware Conversational Dense Retrieval system built on two ideas:

    1. Context-denoised query reformulation — reducing the noise introduced by lengthy conversation histories when reformulating the current query. 2. Automatic mining of supervision signals — generating training signals automatically based on the actual impact of historical turns, instead of relying solely on limited manual annotations.

    Results

    Experiments on two public conversational search datasets demonstrate the improved history modeling capability of HAConvDR, particularly for long conversations with topic shifts.

    Original Abstract

    > Conversational search facilitates complex information retrieval by enabling multi-turn interactions between users and the system. Supporting such interactions requires a comprehensive understanding of the conversational inputs to formulate a good search query based on historical information. In particular, the search query should include the relevant information from the previous conversation turns. However, current approaches for conversational dense retrieval primarily rely on fine-tuning a pre-trained ad-hoc retriever using the whole conversational search session, which can be lengthy and noisy. Moreover, existing approaches are limited by the amount of manual supervision signals in the existing datasets. To address the aforementioned issues, we propose a History-Aware Conversational Dense Retrieval (HAConvDR) system, which incorporates two ideas: context-denoised query reformulation and automatic mining of supervision signals based on the actual impact of historical turns. Experiments on two public conversational search datasets demonstrate the improved history modeling capability of HAConvDR, in particular for long conversations with topic shifts.

    Related Entries

  • A Survey of Conversational Search (ACM, Sep 2025)
  • Engineering Conversational Search Systems: A Review (arXiv:2407.00997)
  • Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
  • CTR-Guided Generative Query Suggestion in Conversational Search (EMNLP)
  • ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval (arXiv:2404.13556)
  • CoSearchAgent: A Lightweight Collaborative Search Agent (arXiv:2402.06363)
  • References

  • Original paper: History-Aware Conversational Dense Retrieval. arXiv:2401.16659

Tags

#conversational-search#dense-retrieval#information-retrieval#query-reformulation#arxiv#nlp#history-modeling

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/178208528