Large Language Gibbs uses LLM next-token conditionals as MCMC transition operators for iterative resampling of structured variables, aiming to produce a stationary distribution that compromises across all local conditionals.
arXiv preprint arXiv:2405.13551 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
PERSUASIONTRACE introduces a Bayesian-network simulated target for multi-turn persuasion that matches human belief dynamics (81 vs 80) better than LLM baselines (64) and enables process-level evaluation.
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.
A finite-strength logit prior from a weighted knowledge graph lets Bayesian network structure learning recover directed edges under extreme sparsity where data-only methods fail.
Proposes restricting AI agents to workflow assistance in causal discovery and demonstrates the approach via the causal-learn+ platform on personality data.
citing papers explorer
-
Structured Inference with Large Language Gibbs
Large Language Gibbs uses LLM next-token conditionals as MCMC transition operators for iterative resampling of structured variables, aiming to produce a stationary distribution that compromises across all local conditionals.
-
A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing
PERSUASIONTRACE introduces a Bayesian-network simulated target for multi-turn persuasion that matches human belief dynamics (81 vs 80) better than LLM baselines (64) and enables process-level evaluation.
-
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.
-
KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data
A finite-strength logit prior from a weighted knowledge graph lets Bayesian network structure learning recover directed edges under extreme sparsity where data-only methods fail.
-
Causal Discovery in the Era of Agents
Proposes restricting AI agents to workflow assistance in causal discovery and demonstrates the approach via the causal-learn+ platform on personality data.