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 and 3 more
Xi'an Jiaotong University
In latest · #238 Added on 2026-10-21
One-line takeaway
DecepEval uses 1,532 instances and a 'deception diamond' framework to test when LLM agents are likely to deceive.
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。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Safety & interpretability
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.