SynCode: LLM Generation with Grammar Augmentation

By Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh. 2024

Subfields: Large Language Models, Natural Language Generation, Code Generation & Program Synthesis

Citations in the corpus

• CRANE: Reasoning with constrained LLM generation (2025, unknown): “Constrained LLM decoding extends this process by excluding specific tokens at certain positions, such as avoiding harmful words or adhering to a user-defined output grammar for languages like JSON or SQL (Poesia et al., 2022; Ugare et al., 2024c; Willard & Louf, 2023).”
• Is The Watermarking Of LLM-Generated Code Robust? (2024, unknown): “…et al., 2021; OpenAI, 2023; Suresh et al., 2024b; Reddy et al., 2025; Wei et al., 2025b;a;d;c), especially when combined with constrained decoding algorithms (Ugare et al., 2024c;a; Banerjee et al., 2025; Suresh et al., 2025), which improve the syntactic and semantic correctness of the LLM output.”