Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Grammar-Aligned Decoding
Kanghee Park, Jiayu Wang, Taylor Berg-Kirkpatrick +2
Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-formed markup. Constrained decoding a…
cs.AI2025
Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
Emmanuel Anaya Gonzalez, Sairam Vaidya, Kanghee Park +3
Constrained decoding enables Language Models (LMs) to produce samples that provably satisfy hard constraints. However, existing constrained-decoding approaches often distort the un…