Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs 事件

Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs arXiv:2606.10852v1 Announce Type: new Abstract: LLM deception is often evaluated through direct markers such as fabricated claims, explicit lies, or strategic concealment. However, many real-world misleading communications do not depend on false statements, rather, they arise from selective treatment of true material facts: omitting adverse evidence, softening unfavorable details, emphasizing favorable details, or replacing