1
Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning
LLM数学推理修复藏着不对称风险，新研究用“守门修复”机制确保替换比保留更安全。
arXiv:2605.24613v1 Announce Type: cross Abstract: Post-hoc repair of LLM mathematical reasoning introduces an asymmetric risk: fixing an incorrect rea…