English(EN) Strong yet Controllable LLM Abstention without Learning to Abstain

新的TAPS方法增强了LLM的弃权和准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了一种名为“先训练准确性，再进行事后选择”（TAPS）的新方法，用于大型语言模型（LLM），以提高它们在不确定时弃权回答问题的能力。这种模块化方法可以实现可控的覆盖范围，并可以使用标准的训练后技术和现有的置信度估计器来实现。与传统的弃权训练方法相比，TAPS在多个LLM和事实问答基准测试中表现出较低的平均风险。 AI

影响通过更好地控制模型何时弃权回答，提高了LLM的可靠性，可能减少幻觉。

排序理由详细介绍LLM新方法的 isto 研究论文。 [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: 8 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM新方法的 isto 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Junwei Zhang, Yifei Wang, Wanli Yang, Hexiang Tan, Rui Tang, Xin Chen, Jingang Wang, Du Su, Fei Sun · 2026-10-27 04:00

强大但可控的LLM在不学习弃权的情况下实现弃权

arXiv:2610.16318v2 Announce Type: replace Abstract: Large language models (LLMs) can reduce hallucination by abstaining from questions they would likely get wrong. Abstention can be implemented outside the model (selective answering) using a confidence threshold that controls the…

本文如何被排名

报道来源 [1]

强大但可控的LLM在不学习弃权的情况下实现弃权

相关实体

相关话题