从链式到图结构，探秘大模型推理内部路径，一篇硬核机理研究。
arXiv:2601.17593v3 Announce Type: replace Abstract: Recent progress in large language models has renewed interest in how multi-step reasoning is repre…
以隐马尔可夫模型为例，揭示从预训练大语言模型中提取可解释算法的前沿方法。
arXiv:2607.22646v1 Announce Type: cross Abstract: Large language models (LLMs) display a striking ability to predict next observations from Hidden Mar…
揭秘RAG中LLM引用生成的内在机制，让AI“引经据典”不再黑箱。
arXiv:2606.28358v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (L…
首次从机制层面揭示图语言模型中图令牌的下沉现象，为理解图结构表示学习提供新视角。
arXiv:2606.03712v1 Announce Type: new Abstract: Graph Language Models (GLMs) have become a promising direction for adapting Large Language Models (LLM…