利用激活几何进行无监督特征挖掘，无需人类标注即可揭示大模型内部表征
arXiv:2607.04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs). M…
用LLM Agent自动发现并优化概念编辑算法，为模型可解释性开辟新路径
Article URL: https://dmodel.ai/concept-erasure/ Comments URL: https://news.ycombinator.com/item?id=48746983 Points: 3 # Comments: 0
揭秘LLM电路发现中的方差来源，为可解释性研究提供新视角
arXiv:2606.16920v1 Announce Type: cross Abstract: Circuit discovery is a key technique in mechanistic interpretability to pinpoint the model component…
新方法实现又快又忠实的函数向量，提升大模型行为控制的可信度与效率
arXiv:2606.05079v1 Announce Type: new Abstract: Function vectors (FVs) are task representations elicited during in-context learning that can be used t…
用问答任务探测大模型隐藏的认知盲区，揭秘AI到底“知道什么却不说”
arXiv:2605.31561v1 Announce Type: new Abstract: Test-time reasoning has become a significant field of study since the introduction of chain-of-thought…
揭秘思维链内部机制，从解码、投影、激活三角度追踪信息流，ACL 2026收录。
arXiv:2507.20758v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanis…