新方法分解不确定性，让LLM代理主动提问澄清，提升交互可靠性。
arXiv:2606.19559v1 Announce Type: new Abstract: Recent position papers argue that the classical aleatoric/epistemic uncertainty framework is insuffici…
不只是谄媚：新研究揭示LLM的顺从行为源于认知不确定性，为理解模型输出偏差提供新视角。
arXiv:2605.27288v1 Announce Type: cross Abstract: Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. …
将中智逻辑引入大语言模型，突破概率总和为一的局限，为认知不确定性提供全新框架。
arXiv:2605.24053v1 Announce Type: new Abstract: Large Language Models (LLMs) are predominantly governed by probabilistic frameworks in which the sum o…
用认知不确定性引导知识蒸馏，解决学生误解分类中数据稀疏与边界模糊难题。
arXiv:2605.14752v1 Announce Type: cross Abstract: Accurately identifying student misconceptions is crucial for personalized education but faces three …