BayesPO: Bayesian Prompt Optimization via Parallel-Tempered Gradient-Guided Discrete MCMC
Prompt optimization adapts large language models (LLMs) without updating model parameters, but many automatic prompt optimizers remain heuristic search procedures over candidate instructions. This paper studies prompt optimization as Bayesian posterior sampling over discrete prompt tokens. We define a posterior distribution by combining a task likelihood term, which rewards prompts that explain input-output examples, with a language-model prior, which favors fluent instructions. This converts prompt optimization into an energy-based posterior sampling problem, for which gradients can be used t
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- FuzzySimilar title/name (fuzzy) · 59%NirDiamant/Prompt_Engineering →
“Fuzzy title match (0.73): “BayesPO: Bayesian Prompt Optimization via Parallel-Tempered ” ≈ “NirDiamant/Prompt_Engineering””
- FuzzySimilar title/name (fuzzy) · 59%linshenkx/prompt-optimizer →
“Fuzzy title match (0.73): “BayesPO: Bayesian Prompt Optimization via Parallel-Tempered ” ≈ “linshenkx/prompt-optimizer””
- LinkedLinked via arxiv author · 85%Junjie Zhou →
“BayesPO: Bayesian Prompt Optimization via Parallel-Tempered Gradient-Guided Discrete MCMC”
- LinkedLinked via arxiv author · 85%Zhijian Ou →
“BayesPO: Bayesian Prompt Optimization via Parallel-Tempered Gradient-Guided Discrete MCMC”