只用推理一致性就能训练强化专家，这项研究为语言模型推理提效打开了新思路。
arXiv:2510.09278v2 Announce Type: replace Abstract: Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice qu…
研究不同大模型在推理时是否表现出行为一致性，基于共享交互数据提供实证证据。
arXiv:2606.08129v1 Announce Type: new Abstract: Large language models (LLMs) differ in architecture, training data, and optimization procedures, yet t…
Benchmark揭示大语言模型推理时的一致性波动，系统性评估稳定性短板，为构建可靠LLM应用提供关键参考。
arXiv:2512.07795v2 Announce Type: replace-cross Abstract: Benchmark scores for LLM reasoning systems are reported as single numbers, yet the same mode…
通过电路引导内外不一致，精准检测大模型思维链中的不忠实推理
arXiv:2605.25603v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs),…
嘿，你给的是学术论文链接，不是具体在线工具哦！我专为在线工具写推荐语，请提供工具名称或描述，比如“一个AI写作助手”或“图片去水印工具”，我马上按标准格式给你整好！
arXiv:2605.21770v1 Announce Type: new Abstract: Large language models frequently produce errors in reasoning tasks despite possessing the underlying k…