← Search

Emmanuel Anaya Gonzalez

2 accepted papers

2025

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective

NeurIPS 2025poster

Constrained decoding enables Language Models (LMs) to produce samples that provably satisfy hard constraints. However, existing constrained-decoding approaches often distort the underlying model distribution, a limitation that is especially problematic in applications like program fuzzing, where one…

Cited by 0SourceScholar
2024

HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis

NeurIPS 2024poster

Many structured prediction and reasoning tasks can be framed as program synthesis problems, where the goal is to generate a program in a \emph{domain-specific language} (DSL) that transforms input data into the desired output. Unfortunately, purely neural approaches, such as large language models (L…

Cited by 11SourcePDFScholar