mlsanityData to 7 Oct 2026

Uncertainty in Language Models: Assessment through Rank-Calibration

arXiv 2404.03163 ↗First posted 4 Apr 2024cs.CL cs.AI cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs. In addition to verbalized confidence elicited via prompting, many uncertainty measures (e.g., semantic entropy and affinity-graph-based measures) have been proposed. However, these measures can differ greatly, and it is unclear how to compare them, partly because they take values over different ranges (e.g., [0,∞) or [0,1]). In this work, we address this issue by developing a novel and practical framework, termed Rank-Calibration, to assess uncertainty and confidence measures for LMs. Our key tenet is that higher uncertainty (or lower confidence) should imply lower generation quality, on average. Rank-calibration quantifies deviations from this ideal relationship in a principled manner, without requiring ad hoc binary thresholding of the correctness score (e.g., ROUGE or METEOR). The broad applicability and the granular interpretability of our methods are demonstrated empirically.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 31 of its 63 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

31 of 63 references.

References · 31

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  10. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  11. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  12. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
19 more
  1. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  2. 2021Ethical and social risks of harm from Language Modelscited by 957
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  4. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  5. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  6. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  7. 2019Measuring Calibration in Deep Learningcited by 443
  8. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  9. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  10. 2019Verified Uncertainty Calibrationcited by 307
  11. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  12. 2020CORD-19: The COVID-19 Open Research Datasetcited by 179
  13. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  14. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 166
  15. 2020Calibration of Neural Networks using Splinescited by 97
  16. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 79
  17. 2019Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensemblescited by 30
  18. 2021On the Calibration and Uncertainty of Neural Learning to Rank Modelscited by 24
  19. 2022T-Cal: An optimal test for the calibration of predictive modelscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 15; 2026: 14.

40 papers.

Sort:

By area:

  1. 2024What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineeringcited by 88
  2. 2025A Survey of Uncertainty Estimation Methods on Large Language Modelscited by 57
  3. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 50
  4. 2024One-Shot Safety Alignment for Large Language Models via Optimal Dualizationcited by 24
  5. 2024Dual Active Learning for Reinforcement Learning from Human Feedbackcited by 19
  6. 2025Reconsidering LLM Uncertainty Estimation Methods in the Wildcited by 17
  7. 2025MUR: Momentum Uncertainty guided Reasoning for Large Language Modelscited by 17
  8. 2024Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generationcited by 16
  9. 2024On Subjective Uncertainty Quantification and Calibration in Natural Language Generationcited by 14
  10. 2024UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generationcited by 14
  11. 2024Uncertainty Quantification in Large Language Models Through Convex Hull Analysiscited by 12
  12. 2024Graph-based Confidence Calibration for Large Language Modelscited by 10
28 more
  1. 2024A Survey of Calibration Process for Black-Box LLMscited by 8
  2. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 6
  3. 2025Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantificationcited by 6
  4. 2026LLMs Should Express Uncertainty Explicitlycited by 6
  5. 2026Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibrationcited by 6
  6. 2025Do Large Language Models (Really) Need Statistical Foundations?cited by 5
  7. 2025Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Taskscited by 5
  8. 2024Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generationcited by 4
  9. 2025MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labelscited by 4
  10. 2025LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertaintycited by 4
  11. 2025Statistical Methods in Generative AIcited by 4
  12. 2026Calibrating Semantic Uncertainty from Observable Language-Model Probabilitiescited by 4
  13. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
  14. 2025ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreakscited by 3
  15. 2025HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Modelscited by 3
  16. 2026VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Modelscited by 3
  17. 2026Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Modelscited by 3
  18. 2025HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answeringcited by 2
  19. 2026Quantifying Consistency in LLM Logical Reasoning via Structural Uncertaintycited by 2
  20. 2025On the Convergence of Moral Self-Correction in Large Language Modelscited by 1
  21. 2026Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Modelscited by 1
  22. 2026Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gainscited by 1
  23. 2026Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurementcited by 0
  24. 2026Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labelingcited by 0
  25. 2026Evaluating the Relevance of Uncertainty Estimators for LLM Hallucinationcited by 0
  26. 2026AsymVerify at SemEval-2026 Task 6: Asymmetric Confidence-Gated Verification for Political Evasion Detectioncited by 0
  27. 2026From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosiscited by 0
  28. 2026On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Modelscited by 0