mlsanityData to 7 Oct 2026

Questionable practices in machine learning

arXiv 2407.12220 ↗First posted 17 Jul 2024cs.LG cs.CL cs.CYcited by 3

Not on the map. Why?

Abstract (arXiv)

Evaluating modern ML models is hard. The strong incentive for researchers and companies to report a state-of-the-art result on some metric often leads to questionable research practices (QRPs): bad practices which fall short of outright research fraud. We describe 44 such practices which can undermine reported results, giving examples where possible. Our list emphasises the evaluation of large language models (LLMs) on public benchmarks. We also discuss "irreproducible research practices", i.e. decisions that make it difficult or impossible for other researchers to reproduce, build on or audit previous research.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 107 of its 228 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

107 of 228 references.

References · 107

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2022Training language models to follow instructions with human feedbackcited by 15,712
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  8. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  9. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  10. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  11. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  12. 2020Measuring Massive Multitask Language Understandingcited by 7,768
38 more
  1. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  2. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  6. 2023Let's Verify Step by Stepcited by 3,598
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  8. 2023Mistral 7Bcited by 3,065
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  11. 2020Extracting Training Data from Large Language Modelscited by 2,144
  12. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  13. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  14. 2024Mixtral of Expertscited by 1,785
  15. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  16. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  17. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  18. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  19. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
  20. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  21. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  22. 2017Deep Reinforcement Learning that Matterscited by 727
  23. 2023Textbooks Are All You Needcited by 561
  24. 2021Dynabench: Rethinking Benchmarking in NLPcited by 447
  25. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  26. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  27. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 388
  28. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 377
  29. 2023Detecting Pretraining Data from Large Language Modelscited by 375
  30. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 325
  31. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 319
  32. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  33. 2023State of What Art? A Call for Multi-Prompt LLM Evaluationcited by 299
  34. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  35. 2023How is ChatGPT's behavior changing over time?cited by 265
  36. 2023Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingcited by 260
  37. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
  38. 2022Data Contamination: From Memorization to Exploitationcited by 234

50 most cited of 107 All 107 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluationcited by 57
  2. 2025Infrastructure for AI Agentscited by 40
  3. 2025Pitfalls in Evaluating Language Model Forecasterscited by 23