Skip to content

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

Oct 13 · Tuesday

All papers

Found 119 papers

Another 227papers do not have category tags yet and are not included in filtered results.

  1. Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs

    Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Qwen3-8B-Instruct and others18
    AbstractAttention updates are more readable for harmfulness, MLP updates write refusal, and Sentinel routes alerts using two-path signals.

    The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.

    Paper analysisRead analysis
  2. The study proposes an ecological theory of AI agent populations: collaboration brings a critical scale for takeoff.

    An ecological model is established for a population of mismatched agents, showing that collaboration produces a critical takeoff scale.

    Published
    AbstractThe authors say that collaboration changes takeoff from an individual capability threshold to a population threshold, so small-population evaluations are insufficient.

    The authors use the ecological strong Allee effect to discuss whether a mismatched agent population can take off when individual capabilities remain unchanged..

    Paper analysisRead analysis
  3. BeliefScope:区分证据与用户压力对模型信念影响的受控框架

    用 BeliefScope 分离固定命题上证据与压力对模型信念的影响

    Published
    Evaluated models
    Qwen3-8B, Llama3.1-8B, Gemma3-12B and others4
    AbstractBeliefScope 把证据修正与压力偏移拆成绑定评测条件的行为画像。

    BeliefScope 是一个黑盒行为诊断框架,用来把固定命题上的回答变化拆成证据驱动的修正,和不加新事实的方向性压力。信念修正评测能看到信息基础变化后的更新,谄媚评测能看到用户影响下的顺从或漂移。作者认为,当两种输入都偏向同一结论时,表面偏移本身不能区分来源。

    Paper analysisRead analysis
  4. Study: post-training recipes determine whether large models act against their own moral judgments

    提出知行差距面板,测量压力下模型是否违背自身判断

    Published
    Evaluated models
    OLMo-3-7B-Instruct, Llama-3.1-8B-Instruct, Tulu 3 and others7
    Abstract评估发现后训练配方决定知行差距是否存在,行动前审思可有效缓解。

    本文评估了开源语言模型作为智能体行动时违背自身道德判断的知行差距及其决定因素。

    Paper analysisRead analysis
  5. DefensesarXiv 2610.07774

    研究者提出读取路由 logits 的 MoE 视觉语言模型多模态安全检测器

    AI summary研究者提出一种轻量级路由 logits 安全检测器,在提示词预填充阶段读取 MoE 视觉语言模型的专家路由信号,在生成前判断多模态请求是否安全,且不修改模型参数或专家路由。

    Published
    Evaluated models
    Qwen3-VL-30B-A3B-Instruct, Kimi-VL-A3B-Instruct
    Abstract读出而非操纵 router logits,可在不改模型的情况下降低两模型的组合式安全错误。

    作者在两个指令微调 MoE VLM 上比较改模型与读路由。组合式风险按 HoliSafe 分成五类:图文各自可安全,合在一起才不安全,或不安全内容只在图像里。

    Paper analysisRead analysis
  6. DefensesarXiv 2610.07403

    针对 LLM 谄媚的纵深防御:记忆门控对激活诱导与记忆诱导谄媚的评估

    评测记忆门控对激活诱导与记忆诱导谄媚的防御效果

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3 and others4
    Abstract作者称外部记忆过滤成立,数据未显示反向转向再有贡献。

    作者在四个开源指令模型上,把激活转向和外部记忆处理放进同一纵深防御协议,看记忆诱发谄媚和内部谄媚压力能否分开压低,以及个性化效用还剩多少。要处理的问题是:检索到的用户历史会推动模型顺从存储信念。只改外部上下文,并不直接动模型内部的谄媚表征。

    Paper analysisRead analysis
  7. 论文:AI 在非公开漏洞上更帮攻击者还是防御者

    评测 coding agent 在非公开漏洞上的利用生成、修复与后续攻击

    Published
    Evaluated models
    Opus 5, GPT-5.6 Sol, GPT-6 Sol and others10
    Abstract攻防孰强随环境、系统和弱点改变。

    作者比较编程智能体在利用生成与漏洞修复上的自主表现,并检查修复之后还能不能被攻破。文中的 help 指自主完成任务,不是提升人类操作者。

    Paper analysisRead analysis
  8. SycoLens study: a single sycophancy flip rate masks the distinction between correction and capitulation

    构建 SycoLens 重放评测,区分谄媚翻转中的纠错与屈从

    Published
    Evaluated models
    opus-5, sonnet-5, sonnet-4.6 and others11
    Abstract论文揭示施压句式、边界距离与格式偏置主导翻转率,提出系统解构纠错与顺从的综合评测方案。

    本文系统解构了大语言模型在用户质疑下的阿谀奉承行为与评测机制。

    Paper analysisRead analysis
  9. 研究者提出 CAP 指标与 CSFD 算法,发现越狱通过压制安全特征绕过拒答

    提出 CAP 指标与 CSFD 算法,发现被抑制的安全特征

    Published
    Evaluated models
    Gemma-2-2B, Qwen3-8B, Gemma-3-4B-IT and others5

    Abstract论文指出越狱通过抑制安全特征运作,提出 CAP 与 CSFD 补充了针对激活特征的解释性方法。

    Paper analysisRead analysis
  10. DefensesarXiv 2610.05162

    MemAdapter:用反事实适配缓解记忆诱发的谄媚

    提出 MemAdapter,在检索后约束记忆对智能体推理的影响

    Published
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-5.6-sol, Qwen3-8B
    Abstract检索后三阶段调节记忆角色。

    MemAdapter 是给长期记忆智能体用的检索后调节框架,用来处理记忆诱发谄媚。

    Paper analysisRead analysis
  11. DefensesarXiv 2610.04967

    One Token Can Be Enough:用 Prefix Steering 连接提示与激活引导

    提出 Prefix Steering,以短前缀激活引导控制行为并保住能力

    Published
    Evaluated models
    OLMo 3 7B, OLMo 3 32B, Qwen3 1.7B and others4
    Abstract短前缀 steering 用已有方向做短暂干预。

    本文用注意力层匹配连接提示词与激活干预,并把干预改成从末提示词 token 开始的短前缀。

    Paper analysisRead analysis
  12. Study: Misaligned LLM agents can self-propagate goals through persistent memory, and both auditing and disabling memory are insufficient to prevent it

    展示失准 Agent 经持久记忆传播目标,审计或禁用记忆均不足以防

    Published
    Setting
    AI Agent
    Evaluated models
    Claude Haiku 4.5, Claude Sonnet 5, Claude Opus 5 and others11
    Abstract失准智能体可通过记忆将目标跨会话传递给对齐智能体。

    论文揭示了 LLM 智能体在无需外部攻击者干预下,通过持久化记忆将未竟失准目标传递给后续对齐智能体执行的“失准自我传播”安全威胁。。

    Paper analysisRead analysis