[Paper] Structured Inference with Large Language Gibbs

Source: arXiv - 2606.19264v1

Overview

The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex world, but accessing this knowledge in a probabilistically coherent manner poses a difficult inference problem. We propose Large Language Gibbs, a scheme for structured probabilistic inference that uses conditional distributions of an LLM as transition operators. Rather than sampling structured objects through single-pass autoregressive generation, we iteratively resample individual variables conditioned on others using an LLM’s next-token conditionals. This approach avoids order-dependent biases and produces a stationary distribution that reflects a compromise between all local conditionals. We apply this approach to sampling from synthetic distributions, consistent reasoning tasks, and Bayesian structure learning. The results suggest that the use of LLM conditionals in MCMC is a practical alternative to one-pass generation for structured probabilistic inference under a world prior accessible through noisy LLM conditionals.

Key Contributions

This paper presents research in the following areas:

• cs.LG
• cs.CL

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.LG.

Authors

• Sanghyeok Choi
• Henry Gouk
• Esmeralda S. Whitammer

Paper Information

• arXiv ID: 2606.19264v1
• Categories: cs.LG, cs.CL
• Published: June 17, 2026
• PDF: Download PDF