Learning to Diagnose and Correct Errors: Towards Moral Sensitivity Acquisition in Large Language Models 文章

ArXiv CS.CL2026-05-27NEWSen作者: Bocheng Chen, Xi Chen, Han Zi, Haitao Mao, Zimo Qi, Xitong Zhang, Kristen Johnson, Guangliang Liu
大语言模型
查看原文 →
关系图谱

Learning to Diagnose and Correct Errors: Towards Moral Sensitivity Acquisition in Large Language Models · 相关技术

相关技术

LLMORMODEPLAlanguage modeldivide-and-conquer partitioningVerseUnifiedStraight-Through EstimatorSEMReferring expression comprehension (REC)Parts-of-Speech (POS) tagsPPRPETNarrative Abstraction BenchmarkLMMlarge language modelsHISForEffort Metric AttentionENAARGANN