1
CoRA: Confidence-Rationale Alignment for Reliable Chain-of-Thought Reasoning
大模型CoT推理中置信度与理由对齐的新方法，GRPO优化让推理更可靠。
arXiv:2606.14961v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning can improve LLM performance, but high answer confidence may be mislea…