揭秘LLM预测时内部表示与表面CoT推理的差异，更直接反映真实校准和忠实性
arXiv:2607.08046v1 Announce Type: new Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chai…
从神经层面拆解大模型「拍马屁」行为的内部机制，一篇被ICML 2026研讨会接收的机械可解释性突破。
arXiv:2607.07003v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement e…
从Claude到开源模型：研究发现LLM内部存在类似人类心理结构的情绪向量，并揭示其因果影响行为。
arXiv:2606.26987v1 Announce Type: cross Abstract: Recent work identified emotion vectors in Claude Sonnet 4.5, which are internal representations that…
探索LLM内部状态提升法律文本分类准确率，为AI可靠应用提供新思路。
arXiv:2606.20929v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being adopted in the legal domain. However, despite th…
大模型如何学会「故意犯错」？多模型研究发现欺骗性对齐的线性表示规律。
arXiv:2605.30381v1 Announce Type: cross Abstract: Deceptive alignment, in which models maintain accurate internal representations while deliberately p…