arXiv 2610.07967 · cs.LG · 2026-10-06
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Yiming Xu, Hongyue Yu, Beihua Yang, Zihan Chen, Yixin Liu, Zhen Peng, Bin Shi, Bo Dong 等 11 人
Xi'an Jiaotong University
在最新榜 #238 本站收录于 2026-10-21
一句话要点
DecepEval 用 1532 个实例和“欺骗钻石”框架，评测 LLM Agent 在什么条件下更容易撒谎。
DecepEval uses 1,532 instances and a 'deception diamond' framework to test when LLM agents are likely to deceive.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：安全与可解释
- Behavioral Compositionality of Sparse Autoencoder Representations ▲110
- Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics ▲55
- U-Space: Uncovering When and Why Uncertainty Arises in Language Models ▲54
- Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures ▲29
- APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces ▲26
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。