1
Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence
研究揭示LLM法官在混合证据下可能做出未授权方向性承诺,需警惕系统风险与安全边界。
arXiv:2606.07834v1 Announce Type: cross Abstract: LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with bot…