Showing cs.AIShow all
3 papers · 1 filter
cs.AI2025
Constrained Adaptive Rejection Sampling
Paweł Parys, Sairam Vaidya, Taylor Berg-Kirkpatrick +1
Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints. Existing approaches to constrained genera…
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…
cs.AI2024
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…