English(EN) ConfRAG: Confidence-Guided Retrieval-Augmenting Generation

新策略使用置信度引导将大语言模型幻觉率降至5%以下

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

研究人员开发了ConfQA，一种旨在显著减少大语言模型（LLMs）幻觉的微调策略。通过训练模型在缺乏置信度时回答“我不确定”，在各种事实性基准测试中，幻觉率已从20-40%降至5%以下。该方法使用阻尼提示和源自事实陈述的训练数据来提高模型的置信度校准。在ConfQA的基础上，ConfRAG被引入作为一种检索增强生成策略，仅在模型指示不确定时触发外部检索，实现了超过95%的准确率，同时将不必要的检索减少了30%以上。 AI

影响这项研究通过减少幻觉和优化检索过程，有望带来更可靠、更高效的大语言模型应用。

排序理由该集群包含一篇学术论文，详细介绍了一种提高大语言模型事实性和检索效率的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种提高大语言模型事实性和检索效率的新方法。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Yin Huang, Yifan Ethan Xu, Kai Sun, Vera Yan, Alicia Sun, Haidar Khan, Jimmy Nguyen, Jingxiang Chen, Mohammad Kachuee, Zhaojiang Lin, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong · 2026-09-07 04:00

ConfRAG：置信度引导的检索增强生成

arXiv:2506.07309v3 Announce Type: replace Abstract: Can Large Language Models (LLMs) be trained to avoid hallucinating factual statements, and can Retrieval-Augmented Generation (RAG) be triggered only when necessary to reduce retrieval and computation costs? In this work, we add…

本文如何被排名

报道来源 [1]

ConfRAG：置信度引导的检索增强生成

相关实体

相关话题