通过引入任务感知机制，直接在结构空间建模LLM输出，提升生成质量与不确定性估计的准确性。
arXiv:2601.21500v2 Announce Type: replace Abstract: In many applications of LLMs, natural language responses often have an underlying structure such a…
揭秘LLMs如何内部计算口头自信度：是即时响应还是自动生成？这项研究打开黑箱，深入模型推理过程。
arXiv:2603.17839v3 Announce Type: replace-cross Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is …
用语义级奖励替代二元反馈，让LLM学会表达真实不确定性，提升高安全场景下的可靠性。
arXiv:2605.15588v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in consequential settings such as medical question answ…
突破二元奖励局限，让语言模型在推理中学会表达自身不确定性，提升可解释性和可靠性。
arXiv:2507.16806v2 Announce Type: replace-cross Abstract: When language models (LMs) are trained via reinforcement learning (RL) to generate natural l…
系统探索多变量对分割不确定性估计的影响，揭示关键敏感因素，为实际应用提供可靠指导
arXiv:2605.15421v1 Announce Type: new Abstract: In this study, we explore in depth a few under-studied topics at the intersection of uncertainty estim…