LLMs Lean on Priors, Not Programming Language Semantics 事件

LLMs Lean on Priors, Not Programming Language Semantics arXiv:2510.03415v3 Announce Type: replace-cross Abstract: Recent work asks whether large language models (LLMs) condition their reasoning on explicit rules rather than statistical regularities from pretraining. Program execution provides a canonical instance: formal semantics define behavior through symbolic transition rules that can be systematically altered under distribution shift. We investigate whether LLMs can condition their reasoni