Have the model write the deterministic transformation rule, not the transformation.

An evaluation of LLM synthesis of rules in Comby, GritQL and ast-grep with GPT-5.4, GPT-oss-120B and Llama3.1-8B across six datasets covering API misuse correction, program repair, API migration and language version migration. GPT-5.4 achieves consistently high rule applicability and produces transformations closest to ground truth on most benchmarks, with non-negligible generalizability through meta-variables. Smaller open-weight models hold up on localized changes and fail on complex migrations. Against the anti-unification algorithm the LLMs win on correctness and lose on applicability, so the pattern is generate-then-verify-applicability. arXiv 2609.03592