# 先前审计-修复上下文使 LLM 验证器阈值偏向宽松

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-17 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmsy78ikf0m9vroz0qaou0mtu
- 原文链接：https://arxiv.org/abs/2608.16003

## AI 摘要

一项针对 ProcessBench 轨迹的研究发现，模型上下文中已有的“审计→修复”完整流程会降低验证器的误报率：在 15 种模型与措辞组合中全部生效，误报率相对长度匹配的对照组下降 2.8 至 11.5 个百分点（降幅 9%–25%）。信号检测分析显示变化源于判断阈值而非判别能力，且人工复核 50 例误报中 82% 确属错误，因此该偏移在该工作点未必有害。

## 正文

Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer. We ask whether that wiring changes what the checker reports. Measuring false alarms on human-verified-correct ProcessBench traces with the present task held byte-identical, we find that a completed audit -> repair episode already in the model's context lowers false alarms in 15 of 15 model x wording combinations, by 2.8 to 11.5 percentage points against a length-matched non-audit control, a 9 to 25% reduction relative to that control. The direction contradicts what the accumulated-message literature predicts: an episode whose audit reported an error lowers false alarms further still, at all five wordings on the model where that manipulation lands cleanly, though a negativity asymmetry predicts more flagging. Decomposing the episode finds repair content and audit verdict complementary: different components carry the effect on different model families. Signal-detection analysis locates the change in the threshold rather than in discrimination -- the criterion moves in 15 of 15 combinations and survives correction in 13 while d' survives in none, though the d' test is half as sensitive by construction -- and a hand audit of 50 false alarms finds 82% simply wrong, so at this operating point the shift need not be harmful. With reasoning enabled the effect keeps its relative size on both models tested, and the threshold reading holds there too.