1
2
MechLens: Late Crystallization of Factual Knowledge Explains Intervention Effectiveness in Language Models
新研究发现LLM事实知识在最后几层突然“结晶”，而非逐层涌现，解释了为何干预后期层能有效减少幻觉。
arXiv:2606.07978v1 Announce Type: new Abstract: Understanding where LLMs store factual knowledge is critical for hallucination mitigation. We systemat…
3
Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
最新研究揭示大语言模型在不同深度层的因果几何动力学规律，为理解模型内部机制提供新视角。
arXiv:2602.04931v2 Announce Type: replace-cross Abstract: Geometric analyses of large language model (LLM) representations reveal structured variation…
4
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
利用稀疏自编码器挖掘模型内部信号，为LLM强化学习数据工程提供全新无监督指引。
arXiv:2605.27354v1 Announce Type: cross Abstract: Model internals encode rich information about how a large language model (LLM) processes its trainin…