BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data 文章

ArXiv CS.CL2026-05-26NEWSen作者: Bo Zou, Chao Xu
查看原文 →
关系图谱

BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data · 相关技术

相关技术

ginODELLMlanguage model远程代码执行（RCE）后训练divide-and-conquer partitioningUCTStraight-Through EstimatorRLHFParts-of-Speech (POS) tagsOWLOTANATMITLMMImage-Conditioned Instance PromptHISGrouped Memorization EvaluationForEffort Metric AttentionEFIchain-of-thoughtCoTARGANN