AI RESEARCH
Pragmatic Reasoning improves LLM Code Generation
arXiv CS.AI
•
ArXi:2502.15835v5 Announce Type: replace-cross Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and counterfactual alternatives. Similar challenges arise in natural language-to-code generation, where user instructions often admit multiple plausible candidate programs. However, direct RSA-style inference is difficult because it requires probability estimation over large spaces of programs and alternative instructions.