zheng et al 2026
Neural topology of Large Language Models
arxiv 2026
Analyzing functional co-activations in LLMs leads to improved efficiency, reliability and hallucination detection
Work to cite in connection with these data:
Zheng Y, Yuan Y, Zhuo Y, Li Y, Kreiman G, Poggio T, Santi, P. (2026). Probing neural topology of Large Language Models. arXiv 2506.010423. PDF