mlsanityData to 14 Oct 2026

Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models

arXiv 2408.10692 ↗First posted 20 Aug 2024cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Uncertainty quantification (UQ) has emerged as a promising approach for detecting hallucinations and low-quality output of Large Language Models (LLMs). However, obtaining proper uncertainty scores is complicated by the conditional dependency between the generation steps of an autoregressive LLM because it is hard to model it explicitly. Here, we propose to learn this dependency from attention-based features. In particular, we train a regression model that leverages LLM attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens. To incorporate the recurrent features, we also suggest a two-staged training procedure. Our experimental evaluation on ten datasets and three LLMs shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 38 of its 66 references that are in the map. First posted on arXiv 20 Aug 2024.

Builds on

38 of 66 references.

References · 38

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  10. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  11. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  12. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
26 more
  1. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  2. 2018CoQA: A Conversational Question Answering Challengecited by 683
  3. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  4. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  5. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 535
  6. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
  7. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 288
  8. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  9. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
  10. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  11. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 162
  12. 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similaritiescited by 159
  13. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 142
  14. 2019A Question-Entailment Approach to Question Answeringcited by 134
  15. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
  16. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  17. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 99
  18. 2024Information Flow Routes: Automatically Interpreting Language Models at Scalecited by 95
  19. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 81
  20. 2023Do Androids Know They're Only Dreaming of Electric Sheep?cited by 67
  21. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  22. 2024Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Modelscited by 44
  23. 2019Mitigating Uncertainty in Document Classificationcited by 22
  24. 2024LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Modelscited by 16
  25. 2023Uncertainty Estimation on Sequential Labeling via Uncertainty Transmissioncited by 10
  26. 2023Density Uncertainty Layers for Reliable Uncertainty Estimationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2025Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Headscited by 16
  2. 2026AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generationcited by 1
  3. 2026HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Modelscited by 1
  4. 2026Failing to See or Failing to Know? Attributing Errors in Vision-Language Modelscited by 1
  5. 2026Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgmentscited by 0
  6. 2026Uncertainty Quantification for Large Language Diffusion Modelscited by 0
  7. 2026Evaluation Pitfalls and Sparsity Limitations in LLM-based Confidence Estimates for Classificationcited by 0
  8. 2026When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Studycited by 0
  9. 2026ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Mapscited by 0