mcmc

Tag

Cards List
#mcmc

BayesPO: Bayesian Prompt Optimization via Parallel-Tempered Gradient-Guided Discrete MCMC

arXiv cs.CL · 6d ago Cached

This paper presents BayesPO, a Bayesian prompt optimization framework using gradient-guided discrete MCMC with parallel tempering, achieving improved accuracy on instruction-induction tasks.

0 favorites 0 likes
#mcmc

Depth-Entropy Guided Sampling for Training-Free LLM Reasoning

arXiv cs.LG · 2026-07-14 Cached

Introduces Depth-Entropy Guided Sampling (DEGS), a training-free test-time method that exploits layer-wise entropy collapse in LLMs to improve reasoning without RL training, achieving competitive results with RL-posttrained models.

0 favorites 0 likes
#mcmc

Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling

arXiv cs.LG · 2026-06-10 Cached

This paper introduces Entropy-Guided Power Sampling (EGPS), a training-free and verifier-free sampler that improves the efficiency of power sampling for enhancing base language model reasoning. EGPS achieves up to 12.6x speedup over standard Metropolis-Hastings sampling while reaching best or tied-best accuracy on benchmarks like MATH500, HumanEval, and GPQA.

0 favorites 0 likes
#mcmc

LLM Explainability with Counterfactual Chains and Causal Graphs

Hugging Face Daily Papers · 2026-06-04 Cached

This paper proposes a four-phase method for constructing causal graphs that model LLM inference processes, using counterfactual augmentation to enable stable causal discovery and provide transparent, concept-level explainability.

0 favorites 0 likes
#mcmc

bde: A Python Package for Bayesian Deep Ensembles via MILE

arXiv cs.LG · 2026-05-15 Cached

bde is a Python package that brings sampling-based Bayesian Deep Learning to practitioners via the MILE method, combining JAX's speed with scikit-learn's API for tabular supervised learning tasks.

0 favorites 0 likes
← Back to home

Submit Feedback