cs.AI, cs.LG, stat.ME

Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning

arXiv:2603.10377v2 Announce Type: replace-cross
Abstract: Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Causal Concept Graphs (CCG): a directed acyclic graph …