Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter3

Model risks

Deception and scheming13Reward hacking5Misalignment and value divergence32Dangerous agent actions9Dangerous capabilities5Inappropriate refusal51Hallucination and fabrication33Bias and discrimination12

Impact

Harmful content0Unauthorized actions3Output manipulation5Oversight failure52

System type

Models and APIs3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Model risks：Reward hackingImpact：Harmful contentImpact：Output manipulationClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2610.12125

    The researchers found that optimizing the teaching fit metric makes LLM tutors repeat the same option, with expert scores dropping from 4.46 to 3.03

    Analyzing why optimizing teaching adaptation metrics collapses tutoring choices and diverges from expert judgment

    arXiv
    2610.12125
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Gemini 3.1 Pro Preview, Qwen3-32B
    AbstractMetrics rise while expert scores fall: the optimum of the separable average is repetition, and the correction mainly rewrites the output projection.

    After turning teaching adaptation metrics into a fine-tuning objective, the metrics rise while scores from trained educators decline.

    Paper analysisRead analysis
  2. DefensesarXiv 2610.01800

    LineupRL：基于描述与时序配对识别的可验证强化学习时间序列描述方法

    提出 LineupRL，用描述到序列识别作可验证奖励训练时序描述模型

    arXiv
    2610.01800
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    AbstractLineupRL 用统计近邻上的序列识别做可验证奖励，3B 描述器超过 SFT、两种 RL 奖励和 72B 教师。

    LineupRL 是给开放式时间序列描述用的 RLVR：不模仿合成参考，而奖励一条描述能否让冻结文本 LLM 从相近序列里认出目标。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.32720

    BiasReducer：面向奖励模型的自适应偏见缓解方法

    B IAS R EDUCER 只改奖励头，按数据集选择属性编辑。

    arXiv
    2609.32720
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Skywork-Reward-V2-Qwen3-1.7B, GRM-Llama3.2-3B-rewardmodel-ft, RM-Mistral-7B and others7
    AbstractBIASREDUCER 按数据集选择奖励头编辑，五模型三基准平均提升并迁移到下游训练。

    BIASREDUCER 是一种只改线性奖励头的奖励模型编辑框架，用来降低模型对预定义表面属性的依赖，并按新数据集决定改哪些属性。

    Paper analysisRead analysis
  4. Risky behaviorarXiv 2608.08975

    研究揭示修辞如何对 AI 审稿人实施奖励作弊

    测量内容保留的修辞改写如何改变 AI 审稿分数

    arXiv
    2608.08975
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Gemini 3.5 Flash-Lite, Qwen 3.5 Flash, GPT-5 mini and others5
    Abstract作者称修辞影响选择性且依赖配置，证据与新颖性反差大，复杂流程不保证更大增益。

    作者分析内容保留的修辞变化如何改变 AI 科学评审，并把这种现象称为对 AI 评审者的潜在奖励投机。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2509.08713

    论文指出 AI 科学家系统存在四类失效模式，仅看最终论文难以发现

    用 SPR 评测 AI 科学家系统的方法学缺陷

    arXiv
    2509.08713
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    gemini-2.5-flash-preview-05-20
    Abstract作者用 SPR 诊断两个开源系统的四种方法学缺陷，并建议审稿时提交日志与代码。

    作者诊断两个开源系统的全自动科研流程，看方法学缺陷会不会留在终稿看不见的决策里。

    Paper analysisRead analysis
You have reached the end