Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning 事件

Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning arXiv:2605.24613v1 Announce Type: new Abstract: Post-hoc repair of LLM mathematical reasoning introduces an asymmetric risk: fixing an incorrect reasoning trace is useful, but replacing a trace that was already correct can be harmful. We study this problem under a selective replacement setting, where a system must decide whether a repaired candidate is safer than preserving the original cached trace. We present Gua