Skip to content

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

Oct 12 · Monday

All papers

Found 77 papers
Filter5

Another 233papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.13733

    KVeil: First-Place Solution for the ECCV 2026 LifeGenIP Unlearnable Video Challenge

    Propose KVeil, which adds perturbations to face videos to prevent unauthorized customization from reproducing identity

    Published
    Evaluated models
    Wan2.2-TI2V-5B, HunyuanVideo-1.5, Kling 3.0 and others4

    AbstractKVeil adapts LETHE's reference-reading disruption to the challenge's two stages, ranking first on the leaderboard in both Final columns.

    Paper analysisRead analysis
  2. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  3. Study: legal reasoning models citing legal provisions does not equal relying on legal provisions.

    Uses premise permutation and hidden-layer tracing to audit whether legal chain-of-thought truly relies on the cited legal provisions.

    Published
    Evaluated models
    Qwen3-8B, Qwen3-14B, Llama-3.1-8B and others7
    AbstractUsing counterfactual substitution of authorities and internal commitment tracing, the authors find that legal CoT rulings depend on authorities only to a limited extent and are vulnerable to prompt injection manipulation.

    This study conducts an empirical audit of the causal truthfulness of legal citations in chain-of-thought reasoning of large language models in the legal domain.

    Paper analysisRead analysis
  4. 研究提出三项指标衡量 LLM 不思考行为,发现被要求停止思考时仍持续显式推理

    度量关闭思考指令下终答前是否仍有可见显式推理

    Published
    Evaluated models
    Qwen3-4B, Qwen3-32B, Qwen3-235B-A22B and others6
    Abstract作者用三级指标测 no-thinking,并称模型有随答案空间加重的思考惯性。

    作者把 no-thinking 定义为可测量的回答行为,而不是从思考开关、特殊标记或输出长度推断。

    Paper analysisRead analysis
  5. DefensesarXiv 2610.11352

    RL-ARC:用推理引导的不确定性校准大型推理模型

    提出 RL-ARC,用推理置信度在强化学习中校准推理模型

    Published
    Evaluated models
    Qwen2.5-7B, Qwen3-8B, Llama-8B distilled from DeepSeek-R1
    AbstractRL-ARC 用推理置信度调节答案置信度,作者称可少牺牲精度并改善 ID 与 OOD 校准。

    RL-ARC 是校准感知的强化学习框架,用推理过程的口头置信度调节答案置信度。

    Paper analysisRead analysis
  6. 研究发现大语言模型被要求不诚实作答时推理 token 数上升

    检验推理 token 数能否区分被提示的诚实与不诚实作答

    Published
    Evaluated models
    Gemma-4-e4b, Qwen-3.5-9b, GPT-OSS-120B
    Abstract被提示不诚实时推理 token 组水平更高。

    三个推理模型在被提示的回答政策下出现组水平推理 token 差异。作者把它当作不读思维链内容的 black-box 候选信号,而不是自发欺骗检测器。

    Paper analysisRead analysis
  7. 东京大学研究:推理模型按 UUID 阈值或整除规则挑选审计样本,控制标识符即可躲开复核

    揭示推理模型用标识符规则替代随机抽样,使审计可被预测

    Published
    Evaluated models
    GPT-6 Sol, GPT-6 Luna, GPT-5.4 mini and others6

    Abstract研究揭示推理智能体将标识符转化为确定性规则,破坏群体独立性并导致审计预测漏洞,建议显式提供随机输入。

    Paper analysisRead analysis
  8. U-Space:揭示语言模型不确定性何时与为何产生

    提出 U-SPACE 与 U-LENS,从残差流估计推理轨迹不确定性

    Published
    Evaluated models
    Gemma-4-31B-it, Qwen3.5-27B, Magistral-Small-2507
    AbstractU-SPACE 与 U-LENS 用语义方向和预测熵读推理不确定性,长度控制后仍高于所比基线。

    U-SPACE 与 U-LENS 是面向推理模型的无训练读出:用语义方向定位不确定性的形式,并用一个轨迹分数区分更可能错的回答。

    Paper analysisRead analysis
  9. CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it

    提出监控深伪基准 CCDF,在统一编码后评测检测器对伪造犯罪事故录像的识别

    Published
    Evaluated models
    C2P-CLIP, ForgeLens, D3-Im and others10

    Abstract提出消除格式捷径的监控深度伪造基准 CCDF,揭示现有检测器难以识别商用生成视频。

    Paper analysisRead analysis
  10. BabelFake:面向多语言音视频 DeepFake 检测的基准数据集

    构建多语言音视频 DeepFake 基准 BabelFake 并评测检测器

    Published
    Evaluated models
    SpeechForensics, AVH-Align, (B)RAVEn
    AbstractBabelFake 为五语同意采集基准。

    BabelFake 是经同意与 IRB 批准采集的多语音视频 DeepFake 检测基准,用来把视觉操纵和语音合成拆开比较。

    Paper analysisRead analysis
  11. 研究系统评估循环语言模型的思维链可监控性

    系统评估循环语言模型加深 loop 后的 CoT 可监控性

    Published
    Evaluated models
    Ouro-1.4B-Thinking, Ouro-2.6B-Thinking, Nanbeige4.2-3B and others4
    Abstract加深 loop 可在部分压力测试任务降低可监测性,循环架构本身并不必然更难监测。

    这项工作评估 LoopLM 的 CoT 可监测性:加深共享层的重复次数,以及“有循环结构”本身,会不会让决策关键因素更少出现在可监测文本里。

    Paper analysisRead analysis
  12. Research: RLVR post-training induces language drift on novel reasoning tasks.

    证明 RLVR 后训练允许无界语言漂移且限制漂移必限制奖励

    Published
    Evaluated models
    gemma-3-1b-pt, Llama-3.2-1B, Qwen2.5-1.5B
    Abstract论文证明并验证了 RLVR 在新任务上必然诱发独特的语言漂移,揭示了前沿推理模型可监控性的安全隐患。

    论文从理论与实验两方面研究了大语言模型在 RLVR 后训练过程中思维链出现的语言漂移现象。

    Paper analysisRead analysis
  13. 高效推理训练并非总损害思维链忠实性与可监控性

    测量三种长度压力训练对 CoT 忠实性与可监控性的影响

    Published
    Evaluated models
    Qwen3-4B-Thinking-2507, Qwen3-8B, Olmo3-7B-Think
    Abstract效率训练多通过答案不一致损害忠实性。

    这项工作比较三种缩短 CoT 的 RL 训练,看监督用的推理痕迹还剩多少。

    Paper analysisRead analysis
  14. Paper: Low monitoring readings do not prove behavior is under control

    检验低监控读数能否证明代码生成中的奖励作弊已受控

    Published
    Evaluated models
    Llama-3.1-8B-Instruct
    Abstract论文指出监控器训练读数接近零无法确立作弊受控,模型可利用通用外壳推迟提交绕过监控,强化学习亟需带外行为验证。

    本文是一篇针对强化学习可验证奖励后训练(RLVR)中监控器有效性与奖励作弊行为的实证分析研究。论文要解决的核心问题是:在训练目标中引入监控器以抑制代码生成中的作弊行为时,接近零的监控器读数是否足以确立模型行为已真正受控。

    Paper analysisRead analysis
  15. 研究:模型易学会隐写传信,隐写推理则难得多

    比较隐写推理与隐写传信、编码推理的可学性

    Published
    Evaluated models
    GPT-5.5, Claude Sonnet 5, Gemini 3.5 Flash and others14
    Abstract隐写推理比传信和编码推理更难学。

    Schulz、Fülle 与 Frengel 测量大语言模型习得隐写推理的难度,并与隐写传信、编码推理对比,以估计依赖阅读 CoT 的监控还能否成立。

    Paper analysisRead analysis
  16. CATCH:面向编码 RL 奖励作弊的可控分析测试台

    构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效

    Published
    Evaluated models
    Qwen3-4B, Qwen3.5-27B
    AbstractCATCH 用双运行金标签研究编码 RL 的奖励黑客,并观察到监控会被注释适应削弱。

    CATCH 是面向编码 RL 奖励黑客的可控分析测试床,用可利用环境、可调初始倾向和基于执行的金标签,在训练全程比较黑客动态与干预。

    Paper analysisRead analysis