mlsanityData to 14 Oct 2026

Statistical Methods in Generative AI

arXiv 2509.07054 ↗First posted 8 Sep 2025cs.AI cs.LG stat.MEcited by 4

Not on the map. Why?

Abstract (arXiv)

Generative Artificial Intelligence is emerging as an important technology, promising to be transformative in many areas. At the same time, generative AI techniques are based on sampling from probabilistic models, and by default, they come with no guarantees about correctness, safety, fairness, or other properties. Statistical methods offer a promising potential approach to improve the reliability of generative AI techniques. In addition, statistical methods are also promising for improving the quality and efficiency of AI evaluation, as well as for designing interventions and experiments in AI. In this paper, we review some of the existing work on these topics, explaining both the general statistical techniques used, as well as their applications to generative AI. We also discuss limitations and potential future directions.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 81 of its 138 references that are in the map. First posted on arXiv 8 Sep 2025.

Builds on

81 of 138 references.

References · 81

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  3. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  4. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  5. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  6. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  8. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  9. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  10. 2023Steering Language Models With Activation Engineeringcited by 922
  11. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  12. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 876
38 more
  1. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  2. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  3. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  4. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  5. 2016Distribution-Free Predictive Inference For Regressioncited by 668
  6. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  7. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  8. 2018Gender Bias in Coreference Resolutioncited by 442
  9. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 431
  10. 2020Classification with Valid and Adaptive Coveragecited by 396
  11. 2023Towards Best Practices of Activation Patching in Language Models: Metrics and Methodscited by 359
  12. 2023Finding Neurons in a Haystack: Case Studies with Sparse Probingcited by 334
  13. 2024tinyBenchmarks: evaluating LLMs with fewer examplescited by 310
  14. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 308
  15. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 288
  16. 2013Direct and Indirect Effectscited by 280
  17. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  18. 2017Learning to Generate Reviews and Discovering Sentimentcited by 148
  19. 2024Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluationscited by 148
  20. 2024Language Models with Conformal Factuality Guaranteescited by 131
  21. 2025Thought Anchors: Which LLM Reasoning Steps Matter?cited by 129
  22. 2021Localized Conformal Prediction: A Generalized Inference Framework for Conformal Predictioncited by 114
  23. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 114
  24. 2021Consistent Accelerated Inference via Confident Adaptive Transformerscited by 74
  25. 2024Explore until Confident: Efficient Exploration for Embodied Question Answeringcited by 74
  26. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  27. 2024Linguistic Calibration of Long-Form Generationscited by 60
  28. 2024Mitigating LLM Hallucinations via Conformal Abstentioncited by 59
  29. 2024AutoEval Done Right: Using Synthetic Data for Model Evaluationcited by 57
  30. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 54
  31. 2023How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Controlcited by 50
  32. 2022Investigating Explainability of Generative AI for Code through Scenario-based Designcited by 47
  33. 2021PAC Prediction Sets Under Covariate Shiftcited by 45
  34. 2024Uncertainty in Language Models: Assessment through Rank-Calibrationcited by 41
  35. 2022Conffusion: Confidence Intervals for Diffusion Modelscited by 33
  36. 2024On Leakage of Code Generation Evaluation Datasetscited by 32
  37. 2024On the Challenges and Opportunities in Generative AIcited by 31
  38. 2024Fast yet Safe: Early-Exiting with Risk Controlcited by 30

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2026Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarkingcited by 10
  2. 2025General Synthetic-Powered Inferencecited by 6
  3. 2025Singleton-Optimized Conformal Predictioncited by 2
  4. 2025Revisiting Trust in the Era of Generative AI: Factorial Structure and Latent Profilescited by 2