从第一原理出发，揭示LLM可提取记忆研究中两种相反的效度陷阱，平衡过度提取与不可靠证据的争议。
arXiv:2607.12649v1 Announce Type: new Abstract: Recent work on extractable memorization in LLMs suffers from two contrasting validity problems. Some s…
提出一种新型稀疏块注意力机制Proxy Block-CAGE，有望提升长序列建模效率并降低计算开销。
Hi, I'm a PhD student in Bioinformatics/Computational Biology with a software engineering background, I'm trying to pivot toward AI/ML research. I'm f…
LLM置信度评分尺度（0-100）并非中性设计，新研究揭示其对元认知表现的显著影响。
arXiv:2603.09309v2 Announce Type: replace Abstract: Verbalized confidence, in which LLMs report a numerical certainty score, is widely used to estimat…
首次揭示大语言模型如何处理时间偏好概念，深入分析其内部机制与功能表现。
arXiv:2606.05194v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being deployed to make decisions that require trading …