mlsanityData to 14 Oct 2026

Efficient multi-prompt evaluation of LLMs

arXiv 2405.17202 ↗First posted 27 May 2024cs.CL cs.AI cs.LGcited by 73

Not on the map. Why?

Abstract (arXiv)

Most popular benchmarks for comparing LLMs rely on a limited set of prompt templates, which may not fully capture the LLMs' abilities and can affect the reproducibility of results on leaderboards. Many recent works empirically verify prompt sensitivity and advocate for changes in LLM evaluation. In this paper, we consider the problem of estimating the performance distribution across many prompt variants instead of finding a single prompt to evaluate with. We introduce PromptEval, a method for estimating performance across a large set of prompts borrowing strength across prompts and examples to produce accurate estimates under practical evaluation budgets. The resulting distribution can be used to obtain performance quantiles to construct various robust performance metrics (e.g., top 95% quantile or median). We prove that PromptEval consistently estimates the performance distribution and demonstrate its efficacy empirically on three prominent LLM benchmarks: MMLU, BIG-bench Hard, and LMentry; for example, PromptEval can accurately estimate performance quantiles across 100 prompt templates on MMLU with a budget equivalent to two single-prompt evaluations. Moreover, we show how PromptEval can be useful in LLM-as-a-judge and best prompt identification applications.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Builds on 28 of its 54 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

28 of 54 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023Mistral 7Bcited by 3,164
  7. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  9. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
  10. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 868
  11. 2023Large Language Models as Optimizerscited by 864
  12. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
16 more
  1. 2023State of What Art? A Call for Multi-Prompt LLM Evaluationcited by 310
  2. 2024tinyBenchmarks: evaluating LLMs with fewer examplescited by 310
  3. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
  4. 2023Anchor Points: Benchmarking Models with Much Fewer Examplescited by 86
  5. 2024Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvementscited by 83
  6. 2023Efficient Benchmarking of Language Modelscited by 71
  7. 2021Comparing Test Sets with Item Response Theorycited by 57
  8. 2023Prompt Engineering a Prompt Engineercited by 53
  9. 2023PromptBench: A Unified Library for Evaluation of Large Language Modelscited by 44
  10. 2023How Predictable Are Large Language Model Capabilities? A Case Study on BIG-benchcited by 34
  11. 2023Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learningcited by 31
  12. 2021Fixed-Budget Best-Arm Identification in Structured Banditscited by 22
  13. 2022LMentry: A Language Model Benchmark of Elementary Language Taskscited by 22
  14. 2024Label-Efficient Model Selection for Text Generationcited by 19
  15. 2023SPELL: Semantic Prompt Evolution based on a LLMcited by 15
  16. 2023The ICL Consistency Testcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 34; 2026: 35.

73 papers.

Sort:

By area:

  1. 2024POSIX: A Prompt Sensitivity Index For Large Language Modelscited by 59
  2. 2025Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMscited by 30
  3. 2025How Benchmark Prediction from Fewer Data Misses the Markcited by 28
  4. 2024Sloth: scaling laws for LLM skills to predict multi-benchmark performance across familiescited by 24
  5. 2026Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judgescited by 24
  6. 2025DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluationcited by 21
  7. 2025Towards LLMs Robustness to Changes in Prompt Format Stylescited by 21
  8. 2025SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Modelscited by 19
  9. 2024LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Contentcited by 17
  10. 2025Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Stylescited by 16
  11. 2025ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Momentscited by 11
  12. 2025MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Modelscited by 10
38 more
  1. 2025Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systemscited by 10
  2. 2026Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetrycited by 8
  3. 2025Evalita-LLM: Benchmarking Large Language Models on Italiancited by 7
  4. 2025Accelerating Unbiased LLM Evaluation via Synthetic Feedbackcited by 7
  5. 2026Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarkingcited by 7
  6. 2025PairBench: Are Vision-Language Models Reliable at Comparing What They See?cited by 6
  7. 2025Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systemscited by 6
  8. 2026ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Modelscited by 6
  9. 2026Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluationcited by 6
  10. 2025Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustnesscited by 5
  11. 2025The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formattingcited by 5
  12. 2025Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Promptscited by 4
  13. 2025Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoningcited by 4
  14. 2024Bilingual Evaluation of Language Models on General Knowledge in University Entrance Exams with Minimal Contaminationcited by 3
  15. 2025Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMscited by 3
  16. 2025SineProject: Machine Unlearning for Stable Vision Language Alignmentcited by 3
  17. 2026Ensembling Language Models with Sequential Monte Carlocited by 3
  18. 2026Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Resultscited by 3
  19. 2025PAFT: Prompt-Agnostic Fine-Tuningcited by 2
  20. 2025MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinationscited by 2
  21. 2025Taming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedbackcited by 2
  22. 2025Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluatorcited by 2
  23. 2025A Latent Variable Framework for Scaling Laws in Large Language Modelscited by 2
  24. 2025Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Modelscited by 2
  25. 2025Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisionscited by 2
  26. 2026On the Paradoxical Interference between Instruction-Following and Task Solvingcited by 2
  27. 2026Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicitycited by 2
  28. 2026Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorizationcited by 2
  29. 2026How Open Must Language Models be to Enable Reliable Scientific Inference?cited by 2
  30. 2026AI Native Asset Intelligencecited by 2
  31. 2026Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baselinecited by 2
  32. 2026Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Datacited by 2
  33. 2026Quantifying Ranking Uncertainty in LLM Benchmarkscited by 2
  34. 2026ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluationcited by 2
  35. 2025Data Metabolism: An Efficient Data Design Schema For Vision Language Modelcited by 1
  36. 2025LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategycited by 1
  37. 2025Prompting for Performance: Exploring LLMs for Configuring Softwarecited by 1
  38. 2025Instance-level Randomization: Toward More Stable LLM Evaluationscited by 1

50 most cited of 73 All 73 (JSON)