Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence 文章

ArXiv CS.AI2026-06-09NEWSen作者: Haoran Xu

详细信息

来源站点
ArXiv CS.AI
作者
Haoran Xu
文章类型
NEWS
语言
en
发布日期
2026-06-09

摘要

arXiv:2606.07834v1 Announce Type: cross Abstract: LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with both supporting and refuting sources) this is unsafe: when the schema exposes CONFLICTING as the authorized non-directional verdict, returning SUPPORTS/REFUTES is an unauthorized directional commitment, a failure we name Cherry-pick Override (CCO). We define CCO under an explicit task contract and report it with a same-denominator diagnostic protocol paired with matched-coverage bootstrap and an apples-to-apples random-veto null. On AVeriTeC's Conflicting subset (N_C = 150), three-option judges return a directional verdict on more than 84% of mixed-evidence claims; under the typed schema, three-judge majority voting amplifies direction-on-conflict on AVeriTeC (0.887 vs. 0.840; 95% CI [+0.013, +0.080]) but does not replicate on VitaminC-Mixed.

相关事件

暂无数据

相关公司

暂无数据

相关人物

暂无数据