Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 3 papers
Filter4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.

Another 232papers do not have category tags yet and are not included in filtered results.

  1. 论文提出拒答的几何解释:事后安全训练脆弱,预训练期持续安全共训更抗攻击

    解释后验安全的权重几何脆弱性,并提出预训练持续安全共训练

    Published
    Evaluated models
    Qwen-2.5-7B, Qwen-2.5-7B-Instruct, Llama-3-8B and others15

    Abstract论文将后验安全脆弱性归因于正交抑制,并提出通过预训练持续共训练实现具备微调抗性的安全防护。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.04714

    Refusal without refusal: an analysis of safety fine-tuning response structure for reducing language model false refusals

    Proposes Rationale-Only safety fine-tuning, removing the refusal statement to reduce false refusals.

    Published
    Evaluated models
    Llama-3.1-8B, Mistral-7B-v0.3, Gemma-2-9B and others8
    AbstractRemoving the boilerplate refusal statement and training only on the rationale can reduce false refusals, while the compliance rate on harmful queries remains low.

    This is a structural analysis of safety fine-tuning data: false refusals are traced by the authors to formulaic refusal statements in responses, rather than relying only on inference-time remedies.

    Paper analysisRead analysis
You have reached the end