collaborators

6 papers

cs.AI2026

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.LG2026

Learning the Error Patterns of Language Models

Jinwoo Kim, Taylor Berg-KirkPatrick, Loris D'Antoni

When generating outputs for domains with specific validity constraints (e.g., a program should compile), LLMs often fail in a small number of focused ways: for example, by using Py…

cs.LG2026

Continuous Diffusion Models Can Obey Formal Syntax

Jinwoo Kim, Taylor Berg-Kirkpatrick, Loris D'Antoni

Diffusion language models offer a promising alternative to autoregressive models due to their global, non-causal generation process, but their continuous latent dynamics make discr…

cs.CL2026

The Format Tax

Ivan Yee Lee, Loris D'Antoni, Taylor Berg-Kirkpatrick

Asking a large language model to respond in JSON should be a formatting choice, not a capability tax. Yet we find that structured output requirements -- JSON, XML, LaTeX, Markdown…

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…