BayesPrompt: human readable prompts that make sense
Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and important research topic. Optimisation methods which aim at minimising the perplexity of a given answer, however, consistently yield so-called pseudoprompts, unintelligible strings of tokens which can lack human interpretability. We argue that this is a consequence of the ill-posedness of the prompt optimisation task. By reframing the task as a Bayesian posterior inference over prompts, we propose an efficient algorithm to sample prompts which are both efficient (in terms of perplexity) and human read
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.
- PossiblePossibly related (embedding) · 52%Understanding Generative AI: Beyond Chatbots and Prompts - Metro State University →
- FuzzySimilar title/name (fuzzy) · 87%f/prompts.chat →
“Fuzzy title match (0.94): “BayesPrompt: human readable prompts that make sense” ≈ “f/prompts.chat””
- FuzzySimilar title/name (fuzzy) · 59%linshenkx/prompt-optimizer →
“Fuzzy title match (0.73): “BayesPrompt: human readable prompts that make sense” ≈ “linshenkx/prompt-optimizer””
- FuzzySimilar title/name (fuzzy) · 59%NirDiamant/Prompt_Engineering →
“Fuzzy title match (0.73): “BayesPrompt: human readable prompts that make sense” ≈ “NirDiamant/Prompt_Engineering””
- LinkedLinked via arxiv author · 85%Franky Kevin Nando Tezoh →
“BayesPrompt: human readable prompts that make sense”
- LinkedLinked via arxiv author · 85%Ali Hussaini Umar →
“BayesPrompt: human readable prompts that make sense”
- LinkedLinked via arxiv author · 85%Alessandro Laio →
“BayesPrompt: human readable prompts that make sense”
- LinkedLinked via arxiv author · 85%Guido Sanguinetti →
“BayesPrompt: human readable prompts that make sense”