mlsanityData to 14 Oct 2026

Uncertainty in Natural Language Generation: From Theory to Applications

arXiv 2307.15703 ↗First posted 28 Jul 2023cs.CL cs.AI cs.LGcited by 61

Not on the map. Why?

Abstract (arXiv)

Recent advances of powerful Language Models have allowed Natural Language Generation (NLG) to emerge as an important technology that can not only perform traditional tasks like summarisation or translation, but also serve as a natural language interface to a variety of applications. As such, it is crucial that NLG systems are trustworthy and reliable, for example by indicating when they are likely to be wrong; and supporting multiple views, backgrounds and writing styles -- reflecting diverse human sub-populations. In this paper, we argue that a principled treatment of uncertainty can assist in creating systems and evaluation protocols better aligned with these goals. We first present the fundamental theory, frameworks and vocabulary required to represent uncertainty. We then characterise the main sources of uncertainty in NLG from a linguistic perspective, and propose a two-dimensional taxonomy that is more informative and faithful than the popular aleatoric/epistemic dichotomy. Finally, we move from theory to applications and highlight exciting research directions that exploit uncertainty to power decoding, controllable generation, self-assessment, selective answering, active learning and more.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 125 of its 201 references that are in the map. First posted on arXiv 28 Jul 2023.

Builds on

125 of 201 references.

References · 125

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  8. 2017On Calibration of Modern Neural Networkscited by 4,960
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  10. 2017Deep reinforcement learning from human preferencescited by 3,912
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  12. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
38 more
  1. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  2. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  3. 2020Learning to summarize from human feedbackcited by 2,588
  4. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  6. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  7. 2018Hierarchical Neural Story Generationcited by 1,193
  8. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  10. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  11. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  12. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  13. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  14. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  15. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  16. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  17. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  18. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  19. 2022PAL: Program-aided Language Modelscited by 652
  20. 2015Generating Sentences from a Continuous Spacecited by 612
  21. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  22. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  23. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  24. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  25. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 365
  26. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 308
  27. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
  28. 2020Evaluation of Text Generation: A Surveycited by 277
  29. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263
  30. 2022Prompting GPT-3 To Be Reliablecited by 260
  31. 2020Selective Question Answering under Domain Shiftcited by 238
  32. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
  33. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 210
  34. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  35. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  36. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  37. 2019Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasetscited by 175
  38. 2020Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AIcited by 167

50 most cited of 125 All 125 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 21; 2025: 23; 2026: 13.

61 papers.

Sort:

By area:

  1. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  2. 2024The Art of Saying No: Contextual Noncompliance in Language Modelscited by 105
  3. 2024Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?cited by 87
  4. 2024Calibrating Large Language Models Using Their Generations Onlycited by 65
  5. 2025A Survey of Uncertainty Estimation Methods on Large Language Modelscited by 62
  6. 2024Conformal Prediction for Natural Language Processing: A Surveycited by 53
  7. 2024Multicalibration for Confidence Scoring in LLMscited by 46
  8. 2024Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selectioncited by 33
  9. 2023Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledgecited by 32
  10. 2024Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questionscited by 32
  11. 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agentscited by 32
  12. 2024Cycles of Thought: Measuring LLM Confidence through Stable Explanationscited by 29
38 more
  1. 2024Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguitycited by 27
  2. 2025Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answercited by 27
  3. 2024Non-Exchangeable Conformal Language Generation with Nearest Neighborscited by 21
  4. 2024DeLLMa: Decision Making Under Uncertainty with Large Language Modelscited by 21
  5. 2025Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Resultscited by 21
  6. 2025A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputscited by 21
  7. 2025Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Modelscited by 18
  8. 2024Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generationcited by 16
  9. 2025Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Headscited by 16
  10. 2025MetaFaith: Faithful Natural Language Uncertainty Expression in LLMscited by 16
  11. 2024Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?cited by 15
  12. 2024From Loops to Oops: Fallback Behaviors of Language Models Under Uncertaintycited by 14
  13. 2025Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missingcited by 14
  14. 2025When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQAcited by 14
  15. 2024Reconfidencing LLMs from the Grouping Loss Perspectivecited by 11
  16. 2024Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classificationcited by 9
  17. 2024Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Modelscited by 9
  18. 2024"I Never Said That": A dataset, taxonomy and baselines on response clarity classificationcited by 9
  19. 2024Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilitiescited by 7
  20. 2025COPU: Conformal Prediction for Uncertainty Quantification in Natural Language Generationcited by 6
  21. 2025HACK: Hallucinations Along Certainty and Knowledge Axescited by 6
  22. 2025Black-Box Hallucination Detection via Consistency Under the Uncertain Expressioncited by 5
  23. 2023LUNA: A Model-Based Universal Analysis Framework for Large Language Modelscited by 4
  24. 2024Unanswerability Evaluation for Retrieval Augmented Generationcited by 4
  25. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 4
  26. 2025Statistical Methods in Generative AIcited by 4
  27. 2025Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimationcited by 4
  28. 2026The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agentscited by 4
  29. 2025Embracing Diversity: A Multi-Perspective Approach with Soft Labelscited by 3
  30. 2025Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Searchcited by 3
  31. 2026Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variationscited by 3
  32. 2026VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Modelscited by 3
  33. 2026Uncertainty Decomposition for Clarification Seeking in LLM Agentscited by 3
  34. 2024Variability Need Not Imply Error: The Case of Adequate but Semantically Distinct Responsescited by 2
  35. 2025References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluationcited by 2
  36. 2025ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Modelscited by 2
  37. 2026Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoningcited by 2
  38. 2023Human-in-the-loop: Towards Label Embeddings for Measuring Classification Difficultycited by 1

50 most cited of 61 All 61 (JSON)