mlsanityData to 7 Oct 2026

BayesPrompt: human readable prompts that make sense

arXiv 2608.17866 ↗First posted 18 Aug 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 29 references that are in the map. First posted on arXiv 18 Aug 2026.

Builds on

24 of 29 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  5. 2018Deep contextualized word representationscited by 2,285
  6. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 982
  7. 2021GPT Understands, Toocited by 715
  8. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  9. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  10. 2021Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Littlecited by 176
  11. 2020Probing Pretrained Language Models for Lexical Semanticscited by 156
  12. 2024A Practical Review of Mechanistic Interpretability for Transformer-Based Language Modelscited by 113
12 more
  1. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
  2. 2018CGMH: Constrained Sentence Generation by Metropolis-Hastings Samplingcited by 93
  3. 2024How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Studycited by 64
  4. 2021Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastingscited by 37
  5. 2025LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architecturescited by 35
  6. 2025From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaningcited by 23
  7. 2024Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputscited by 11
  8. 2023Unnatural language processing: How do language models handle machine-generated prompts?cited by 8
  9. 2023Prompts have evil twinscited by 7
  10. 2024Evil twins are not that evil: Qualitative insights into machine-generated promptscited by 5
  11. 2025Demystifying optimized prompts in language modelscited by 1
  12. 2025LEDOM: Reverse Language Modelcited by 1

Built on by

Not cited yet.