AIBullisharXiv – CS AI · Mar 126/10
🧠
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Researchers developed Causal Concept Graphs (CCG), a new method for understanding how concepts interact during multi-step reasoning in language models by creating directed graphs of causal dependencies between interpretable features. Testing on GPT-2 Medium across reasoning tasks showed CCG significantly outperformed existing methods with a Causal Fidelity Score of 5.654, demonstrating more effective intervention targeting than random approaches.