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

ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval

Forum topic · 小凯 · 2026-07-05

Summary

ChatRetriever (arXiv:2404.13556, April 2024) is a conversational dense retriever that adapts large language models to accurately interpret user intent from complex multi-turn contexts. The authors—Kelong Mao, Chenlong Deng, Haonan Chen, Fengran Mo, Zheng Liu, Tetsuya Sakai and colleagues—propose a simple and effective dual-learning approach: contrastive learning adapts the LLM for retrieval, while masked instruction tuning on high-quality conversational instruction data enhances understanding of complex sessions. Experiments on five conversational search benchmarks show that ChatRetriever substantially outperforms existing conversational dense retrievers, achieving state-of-the-art performance on par with LLM-based rewriting approaches, while exhibiting superior robustness across diverse conversational contexts. The work highlights the potential of directly adapting LLMs for retrieval with complex inputs, avoiding the extra cost of query rewriting pipelines. This forum entry also situates the paper in the broader conversational search literature, with cross-references to surveys, agentic search methods, and query reformulation work such as ConvGQR.

ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval

Overview

| Field | Content | |------|------| | Title | ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval | | Authors | Kelong Mao, Chenlong Deng, Haonan Chen, Fengran Mo, Zheng Liu, Tetsuya Sakai, et al. (7 authors) | | Published | 2024-04-21 | | Source | https://arxiv.org/abs/2404.13556 | | Type | Academic paper | | Section | Conversational Search |

One-line Summary

ChatRetriever adapts large language models for conversational dense retrieval via a dual-learning approach combining contrastive learning with masked instruction tuning, achieving state-of-the-art performance without requiring LLM-based query rewriting.

Background and Motivation

Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. Traditional pipelines that separate retrieval, ranking, and generation struggle to meet the combined demands of natural language interaction, multi-hop reasoning, and up-to-date knowledge in the LLM era. ChatRetriever was proposed to systematize and push forward the boundaries of theory and practice in this intersection, leveraging the strong generalization capability of LLMs to robustly represent complex conversational sessions for dense retrieval.

Method

The core contribution is a simple and effective dual-learning approach:

1. Contrastive learning adapts the LLM itself for dense retrieval; 2. Masked instruction tuning on high-quality conversational instruction tuning data enhances the model's understanding of complex multi-turn sessions.

This design directly encodes conversational context into dense representations, avoiding a separate query-rewriting stage while inheriting the semantic generalization of the underlying LLM.

Experiments and Results

Per the original abstract:

  • Evaluated on five conversational search benchmarks;
  • Substantially outperforms existing conversational dense retrievers;
  • Achieves state-of-the-art performance on par with LLM-based rewriting approaches;
  • Exhibits superior robustness in handling diverse conversational contexts.
  • Exact numerical results should be verified against the tables in the original PDF.

    Key Takeaways for Search / Rec / Personalization

    1. Architecture: adapting a retriever directly to complex inputs (e.g., conversation sessions) can rival rewriting pipelines, at lower inference cost; 2. Data: high-quality conversational instruction tuning data is critical for complex session understanding; 3. Evaluation: robustness across diverse conversational contexts matters as much as average benchmark scores; 4. Production: latency, cost, and answer trustworthiness remain hard constraints for industrial deployment.

    Related Entries (Cross-references)

  • A Survey of Conversational Search, Sep 2025, ACM
  • Engineering Conversational Search Systems: A Review of Applications
  • Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
  • CTR-Guided Generative Query Suggestion in Conversational Search, EMNLP
  • CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models
  • ConvGQR: Generative Query Reformulation for Conversational Search
  • Original English Abstract

    > Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent complex conversational sessions for dense retrieval. To achieve this, we propose a simple and effective dual-learning approach that adapts LLM for retrieval via contrastive learning while enhancing the complex session understanding through masked instruction tuning on high-quality conversational instruction tuning data. Extensive experiments on five conversational search benchmarks demonstrate that ChatRetriever substantially outperforms existing conversational dense retrievers, achieving state-of-the-art performance on par with LLM-based rewriting approaches. Furthermore, ChatRetriever exhibits superior robustness in handling diverse conversational contexts. Our work highlights the potential of adapting LLMs for retrieval with complex inputs like conversational search sessions and proposes an effective approach to advance this research direction.

    References

  • Original paper: ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval. arXiv: https://arxiv.org/abs/2404.13556

Tags

#conversational-search#dense-retrieval#large-language-models#contrastive-learning#instruction-tuning#information-retrieval#query-understanding

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/178208534