הפרשן כבר יודע: תיקון כיוון קל לתיקון כיוון בקודים מוגבלים

תקציר מקורי באנגליתarXiv:2608.10137v2 Announce Type: replace-cross Abstract: Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step. However, because masking only checks whether each token is valid so far, the resulting distribution over complete outputs diverges from the LM's own distribution conditioned on the grammar, biasing generation toward valid but suboptimal outputs. Online sampling can restore this distribution, but only through costly iterative resampling. Our key insight is that the parser and lexer states that GCD tools already maintain carry a strong signal about future grammatical validity. We introduce SHIM, a lightweight, offline-trained correction of the LM's next-token probabilities, condition