AIBullisharXiv – CS AI · Mar 57/10
🧠
The Geometry of Reasoning: Flowing Logics in Representation Space
Researchers propose a geometric framework showing how large language models 'think' through representation space as flows, with logical statements acting as controllers of these flows' velocities. The study provides evidence that LLMs can internalize logical invariants through next-token prediction training, challenging the 'stochastic parrot' criticism and suggesting universal representational laws underlying machine understanding.