mlsanityData to 7 Oct 2026

LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization

arXiv 2510.13907 ↗First posted 14 Oct 2025cs.CL stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth references (e.g., labeled validation data) that are costly to obtain. We propose the Prompt Duel Optimizer (PDO), a sample-efficient framework for label-free prompt optimization based on pairwise preference feedback from an LLM judge. PDO casts prompt selection as a dueling-bandit problem and combines (i) Double Thompson Sampling to prioritize informative comparisons under a fixed judge budget, with (ii) top-performer guided mutation to expand the candidate pool while pruning weak prompts. Experiments on BIG-bench Hard (BBH) and MS MARCO show that PDO consistently identifies stronger prompts than label-free baselines, while offering favorable quality--cost trade-offs under constrained comparison budgets.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 14 Oct 2025.

Builds on

25 of 39 references.

References · 25

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  3. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  4. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  6. 2024A Survey on LLM-as-a-Judgecited by 1,384
  7. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  8. 2023Large Language Models as Optimizerscited by 830
  9. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  10. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 370
  11. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 270
  12. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
13 more
  1. 2024Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluatorscited by 146
  2. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
  3. 2018Preference-based Online Learning with Dueling Bandits: A Surveycited by 100
  4. 2023Evaluating the Zero-shot Robustness of Instruction-tuned Language Modelscited by 63
  5. 2025A Systematic Survey of Automatic Prompt Optimization Techniquescited by 61
  6. 2015Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problemcited by 51
  7. 2016Double Thompson Sampling for Dueling Banditscited by 42
  8. 2025Self-Supervised Prompt Optimizationcited by 37
  9. 2017Multi-dueling Bandits with Dependent Armscited by 35
  10. 2024Efficient Prompt Optimization Through the Lens of Best Arm Identificationcited by 35
  11. 2024PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Samplingcited by 32
  12. 2025Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Modelscited by 29
  13. 2025Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizerscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferencescited by 2
  2. 2026A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Banditscited by 1
  3. 2026UPA: Unsupervised Prompt Agent via Tree-Based Search and Selectioncited by 1
  4. 2026PrefPO: Pairwise Preference Prompt Optimizationcited by 1
  5. 2026Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Promptscited by 1
  6. 2026The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflowscited by 1
  7. 2026Self-Supervised Skill Optimizationcited by 0
  8. 2026Self-Evolving Coding Rules for AI Coding Agentscited by 0