English(EN) Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study

ThinkGR框架通过思维链推理增强生成式检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-21 11:48

研究人员开发了ThinkGR，一个将思维链（CoT）推理整合到生成式检索系统中的新颖框架。该方法允许在单一生成过程中进行迭代思考和文档识别，解决了处理复杂、多步查询的局限性。ThinkGR采用混合解码策略和两阶段训练方法，以连接自由形式的思维生成与结构化检索目标。实验表明，ThinkGR在四个多跳检索基准测试中取得了最先进的成果，平均性能提高了6.86%。 AI

影响增强了处理复杂查询的检索系统，可能提高知识密集型领域的搜索准确性。

排序理由该集群包含一篇详细介绍新框架和实验结果的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新框架和实验结果的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 108 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Pengjie Ren · 2026-05-21 11:48

将思维链整合到生成式检索中：一项初步研究

While generative retrieval (GR) demonstrates competitive performance on standard retrieval benchmarks, existing approaches directly map queries to document identifiers (docids) without intermediate deliberation, limiting their effectiveness for complex queries that require multi-…

本文如何被排名

报道来源 [1]

将思维链整合到生成式检索中：一项初步研究

相关实体

相关话题