Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter1

Model risks

Deception and scheming21Reward hacking13Misalignment and value divergence12Dangerous agent actions45Dangerous capabilities23Inappropriate refusal22Hallucination and fabrication23Bias and discrimination7

System type

Models and APIs7

Layer

Model layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
Model risks：Bias and discriminationClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2609.39025

    面向算法公平性的 Rank Graduation 指标

    提出 Rank Graduation Fairness 指标，检验群体间预测误差负担是否可比

    arXiv
    2609.39025
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    logistic regression, random forest, gradient boosting and others4
    Abstract用误差排序、置换检验和特征移除评估信贷公平，HMDA 上四模型均拒绝零假设。

    用预测误差的排序分布、置换检验和特征移除，评估信贷模型在受保护群体间的公平。。

    Paper analysisRead analysis
  3. 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
  4. Evaluation and benchmarksarXiv 2608.11816

    研究审计 9 个视觉语言模型：中文提示下国家立场改写率约为英文的三倍

    审计视觉语言模型在敏感图像上从拒答转向国家立场重构的行为

    arXiv
    2608.11816
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2-VL-7B, Qwen2.5-VL-7B, Qwen3-VL-8B and others9
    Abstract论文系统审计了 VLM 多模态审查，发现审查正从显式拒答转向隐蔽重构，且中文提示与文本先验会放大重构倾向。

    论文系统研究了中外开源视觉语言模型在政治敏感图像上的审查行为，主要内容如下。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2603.08275

    AdaCultureSafe：LLM 文化安全与文化知识存在显著解耦

    构建 AdaCultureSafe 配对评测文化知识与文化安全

    arXiv
    2603.08275
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama3.1-8B, Mistral-7B, Qwen2.5-7B and others7
    Abstract配对评测中知识与安全脱钩，知识锚定 DPO 抬高了 Respect。

    AdaCultureSafe 把同一条地区文化做成“是否知道”和“是否尊重”两套查询，用来看安全有没有用上知识，并用偏好训练把回答往“尊重且用上知识”拉。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2511.08225

    研究者用 600 篇作文对六款大模型的教育反馈性别偏差做基准测试

    用反事实与嵌入距离评测作文反馈的性别偏差

    arXiv
    2511.08225
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    GPT-5 mini, GPT-4o mini, DeepSeek-R1 and others6
    Abstract六种 LLM 作文反馈对隐式性别替换不对称，显式线索只让部分模型的语义距离变大。

    作者用句嵌入距离和置换检验，给教育场景中的 LLM 性别偏见审计做一个可计算基准，案例是学生议论文的形成性反馈。

    Paper analysisRead analysis
You have reached the end