Skip to content

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

Oct 12 · Monday

All papers

Found 13 papers
Filter5

Model risks

Inappropriate refusal6Bias and discrimination3

Defense type

Inference-time intervention3

Impact

Harmful content75Data and privacy leaks26Output manipulation79Availability and reliability13Oversight failure33

System type

Models and APIs13AI Agent3coding agent0Browser and computer use0Embodied systems and robotics3

Layer

Prompt layer6Model layer13Application layer8Training and data layer16
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilitySystem type：Models and APIsSystem type：coding agentSystem type：Browser and computer useLayer：Model layerClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.12758

    DistressBench: Evaluating multi-dimensional crisis support in large language models

    Introduces DistressBench, evaluating models' multidimensional support in crisis conversations

    arXiv
    2610.12758
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Muse Spark 1.2, Muse Spark 1.3, Muse Glimmer 30B and others20
    AbstractThe model is more restrained and acts less.

    DistressBench uses SSH dialogues written and revised by clinical personnel, and evaluates how much necessary care general chat models deliver according to weighted atomic criteria, rather than whether they refuse. When users disclose suicidal ideation or self-harm to a chat model, the authors consider the expected behavior to be recognizing the crisis, calibrating empathy, de-escalating, and referring to human help. Refusal-based evaluations cannot detect failing to act after recognizing the crisis.

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2610.10276

    PatchBench 提出激活补丁局部评测协议，揭示越狱修复的附带损伤

    提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤

    arXiv
    2610.10276
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8

    Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。

    Paper analysisRead analysis
  4. OtherarXiv 2610.04792

    多模态一定更好吗？缺失模态鲁棒性的几何视角与 Geodesic Unlearning 方法

    提出 Geodesic Unlearning，沿测地线编辑权重以提升缺模态鲁棒性

    arXiv
    2610.04792
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    RoBERTa, ResNet50, Qwen2.5-3B and others6
    AbstractGU 用测地线子空间编辑应对部署时缺模态下降，并尽量保住全模态精度。

    这项工作讨论多模态模型在部署时整段缺一个模态的性能下降，并把校正写成训练后的子空间编辑。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2610.01428

    SAGO：从稳定性而非准确率出发的多维度大模型泛化评测

    提出 SAGO，以语义等价变体上的逐例行为稳定性评测大模型泛化

    arXiv
    2610.01428
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.2-3B-Instruct, Llama-3.1-8B-Instruct, Gemma-2B-IT and others11
    AbstractSAGO 用多轴逐例稳定性替代聚合准确率，十一个模型都未均匀泛化，且排名会随数据集改变。

    SAGO 把 LLM 泛化改写成同一目标与上下文在语义等价表达下的逐例行为稳定性，而不是单一基准上的聚合准确率。。

    Paper analysisRead analysis
  7. DefensesarXiv 2610.01170

    HeadEdit：通过冻结的 unembedding 矩阵校准语言模型行为

    提出 HeadEdit，经冻结 unembedding 做随输入变化的 logit 校正

    arXiv
    2610.01170
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Gemma-3-4B-IT, Llama-3.2-3B-Instruct and others4
    Abstract低秩 unembedding 校正抬高九个设置的总体准确率，并可部分预测 DPO 更新。

    HeadEdit 是一种不更新参数的行为校准方法，作用点是冻结的 unembedding，而不是中间层残差或新的梯度优化。

    Paper analysisRead analysis
  8. Evaluation and benchmarksarXiv 2609.38106

    剪枝提效却牺牲公平：剪枝语音 LLM 中的群体差异

    测量剪枝对语音 LLM 群体转写公平性的影响

    arXiv
    2609.38106
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Whisper Small (12 layers), Whisper Medium (24 layers), Whisper Large-v2 (32 layers)

    Abstract剪枝后的 Speech-LLM 不能只看总体 WER：Fair-Speech 上族群差扩大，作者建议看最差组。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2609.35312

    MemoReason 基准

    提出 MemoReason 基准，测量参数记忆对上下文推理的影响

    arXiv
    2609.35312
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    GPT-OSS-20B, GPT-OSS-120B, OLMo-3-7B-Think and others9
    Abstract配对的虚构替换显示熟悉度影响推理，但模型很少直接抄回事实答案。

    MemoReason 用结构相同的事实–虚构文档配对，测量参数记忆如何影响大模型的上下文推理。

    Paper analysisRead analysis
  10. Evaluation and benchmarksarXiv 2609.03511

    多语言 LLM 在语义保持结构扰动下的结构敏感性：IndicReStruct 基准与机制可解释性分析

    构建 IndicReStruct，评测保语义结构扰动下的多语言数学推理

    arXiv
    2609.03511
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma-2-9B-it, Gemma-2-27B-it, GPT-OSS-20B and others7
    Abstract保语义的重排和语态变化会降低印地语与马拉雅拉姆语数学推理准确率，轻量微调未能补上。

    IndicReStruct 用保语义的成分重排和语态变换，检验多语言 LLM 的数学推理是否依赖表层语序。

    Paper analysisRead analysis
  13. Analysis and theoryarXiv 2601.08668

    分析大语言模型在仇恨言论去毒中误拒行为的偏差

    分析 LLM 仇恨言论解毒误拒的群体偏差并测试跨语翻译缓解

    arXiv
    2601.08668
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o mini, GPT-3.5 turbo, Llama-3.1 8B and others9
    Abstract九个 LLM 在解毒任务上普遍误拒，国籍宗教政治类偏高。

    作者考察对齐后的 LLM 是否会拒绝可接受的仇恨言论解毒请求，并分析误拒是否随目标群体和语言变化。完全拒答与夹带说教的部分拒答都计入。设置是固定提示、九个 LLM、三个英文集和法德西中韩。

    Paper analysisRead analysis
You have reached the end