PulseAugur
中
实时 22:42:25
English(EN) Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective

新的GOAL框架解决了安全对齐LLM中的过度拒绝问题

一篇新的研究论文介绍了GOAL(Gradient Orthogonalization with contrAstive Learning,梯度正交化与对比学习)框架,旨在解决安全对齐的大型语言模型(LLMs)中过度拒绝的问题。过度拒绝是指LLMs因安全对齐而错误地拒绝无害查询的情况。GOAL框架从表示和优化角度分析了这个问题,指出有害样本和过度拒绝样本的表示在更深层变得难以区分,并且有害梯度与拒绝目标的对齐更强。GOAL旨在通过使过度拒绝梯度与有害梯度正交化,并使用对比学习来增强表示分离,从而减轻过度拒绝,并在多个模型和基准测试中证明了其有效性。 AI

影响 这项研究可能带来能够更好地区分有害和无害查询的LLMs,从而改善用户体验和实用性。

排序理由 该集群包含一篇学术论文,详细介绍了一种改进LLM安全对齐的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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

新的GOAL框架解决了安全对齐LLM中的过度拒绝问题

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
该集群包含一篇学术论文,详细介绍了一种改进LLM安全对齐的新方法。[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, safety
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
3 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]

  1. arXiv cs.AI TIER_1 English(EN) · Chao Chen, Pengyang Shao, Wei Qin, Shijie Hao, Fei Shen, Richang Hong ·

    重新审视安全对齐的大型语言模型中的过度拒绝:一个表征与优化视角

    arXiv:2610.39802v1 Announce Type: new Abstract: Over-refusal is a critical side effect of safety alignment in large language models (LLMs), causing harmless but superficially risky queries to be mistakenly rejected. Despite the effectiveness of existing mitigation methods, why sa…