technique

Large Language Gibbs

techniqueactiveprovisionallarge-language-gibbs-4c6f74bd·1 events·first seen 3d ago

Aliases: Large Language Gibbs

Co-occurring entities

More like this (12)

large language models large language model agents Gibbs Sampling Large Language Models (frontier)LangGraph GLM Diffusion Language Models 1B-scale language models Transformer Language Models LESS: Mutual-Stability Sampling for Diffusion Language Models Scaling Laws for Neural Language Models lambda-scaled structural decoding

Recent events (1)

5arXiv · cs.CL·3d ago·source ↗

Large Language Gibbs: MCMC-based structured probabilistic inference using LLM conditionals

Researchers propose Large Language Gibbs, a structured inference scheme that uses an LLM's conditional token distributions as transition operators in a Gibbs sampling (MCMC) loop, iteratively resampling individual variables rather than generating outputs in a single autoregressive pass. The approach targets order-dependent biases in standard generation and aims to produce a stationary distribution reflecting a coherent compromise across all local conditionals. It is evaluated on synthetic distributions, consistent reasoning tasks, and Bayesian structure learning, showing MCMC-based inference is a practical alternative to one-pass generation for structured probabilistic tasks.

Evaluation and Benchmarking Inference Economics Gibbs Sampling Large Language Gibbs