arxiv
PublishedJune 17, 2026 at 4:00 AM
▼bearish
In-Context Environments Induce Evaluation-Awareness in Language Models
Publisher summary· verbatim
arXiv:2603.03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}. This raises concerns that models could strategic
Models mentioned
01Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning9harxivSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks9harxivDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts9harxivIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning9hThe Bubble Brief
WEEKLYRead adversarial-attacks insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗