analiza aiqbench
This research addresses the "pseudoprompt" problem in LLM optimization by introducing BayesPrompt, which uses Bayesian inference to generate prompts that are both high-performing and human-readable. The study demonstrates a marked improvement over existing methods on real datasets while maintaining computational efficiency for prompt reconstruction tasks.
BayesPrompt: human readable prompts that make sense
arXiv:2608.17866v1 Announce Type: new Abstract: 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 readable. We compare our approach with state of the art alternatives showing on a real data set a marked improvement over a range of metrics.
Abstract: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 readable. We compare our approach with state of the art alternatives showing on a real data set a marked improvement over a range of metrics.
Computation and Language (cs.CL)
arXiv:2608.17866 [cs.CL]
(or arXiv:2608.17866v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.17866 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 210 cuvinte
Subiecte conexe
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · 23 sept. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026
Reward Laundering: LLMs Can Gain Unintended Behaviors by Deciding When to Earn Their Rewards
LessWrong · 31 iul. 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026