Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

arXiv:2606.27378v1 Announce Type: new Abstract: We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal representational failures that benchmark accuracy masks. Existing evaluations conflate representation quality with model capacity. Therefore, failures cannot be attributed to the representation rather than to the model that processes it. We formalize four functional axioms (Caus...

arXiv cs.CL ·Fahd Seddik, Fatemeh Fard ·
compartilhar: