mlsanityData to 7 Oct 2026

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

arXiv 2405.20003 ↗First posted 30 May 2024cs.LG cs.AI cs.CLcited by 156

Not on the map. Why?

Abstract (arXiv)

Uncertainty quantification in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. In particular, uncertainty can be used to improve the trustworthiness of LLMs by detecting factually incorrect model responses, commonly called hallucinations. Critically, one should seek to capture the model's semantic uncertainty, i.e., the uncertainty over the meanings of LLM outputs, rather than uncertainty over lexical or syntactic variations that do not affect answer correctness. To address this problem, we propose Kernel Language Entropy (KLE), a novel method for uncertainty estimation in white- and black-box LLMs. KLE defines positive semidefinite unit trace kernels to encode the semantic similarities of LLM outputs and quantifies uncertainty using the von Neumann entropy. It considers pairwise semantic dependencies between answers (or semantic clusters), providing more fine-grained uncertainty estimates than previous methods based on hard clustering of answers. We theoretically prove that KLE generalizes the previous state-of-the-art method called semantic entropy and empirically demonstrate that it improves uncertainty quantification performance across multiple natural language generation datasets and LLM architectures.

Key facts. Cited by 156 papers in the map (data through 7 Oct 2026). Builds on 50 of its 77 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

50 of 77 references.

References · 50

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2023Mistral 7Bcited by 3,065
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  10. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  11. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  12. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
38 more
  1. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  2. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  3. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  4. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  5. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  6. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  7. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  8. 2023The Falcon Series of Open Language Modelscited by 526
  9. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  10. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  11. 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 342
  12. 2020Calibration of Pre-trained Transformerscited by 307
  13. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 299
  14. 2021Unsolved Problems in ML Safetycited by 291
  15. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  16. 2023In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steeringcited by 240
  17. 2023Fine-tuning Language Models for Factualitycited by 219
  18. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  19. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  20. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  21. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  22. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  23. 2023Conformal Language Modelingcited by 163
  24. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  25. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  26. 2023Bayesian Low-rank Adaptation for Large Language Modelscited by 112
  27. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 85
  28. 2020Controlled Hallucinations: Learning to Generate Faithfully from Noisy Datacited by 83
  29. 2018Quantifying Uncertainties in Natural Language Processing Taskscited by 79
  30. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 79
  31. 2023Self-Evaluation Improves Selective Generation in Large Language Modelscited by 74
  32. 2019Calibration of Encoder Decoder Models for Neural Machine Translationcited by 67
  33. 2020Mat'ern Gaussian Processes on Graphscited by 65
  34. 2023Selectively Answering Ambiguous Questionscited by 63
  35. 2022Information Theory with Kernel Methodscited by 37
  36. 2023Trapping LLM Hallucinations Using Tagged Context Promptscited by 34
  37. 2023VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distributioncited by 17
  38. 2021Non-separable Spatio-temporal Graph Kernels via SPDEscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 59; 2026: 83.

156 papers.

Sort:

By area:

  1. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
  2. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  3. 2025A Survey of Uncertainty Estimation Methods on Large Language Modelscited by 57
  4. 2024BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Modelscited by 48
  5. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  6. 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Makingcited by 36
  7. 2024Improving Uncertainty Estimation through Semantically Diverse Language Generationcited by 34
  8. 2024ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Modelscited by 28
  9. 2025Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similaritycited by 26
  10. 2025SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reductioncited by 24
  11. 2025The Illusion of Progress: Re-evaluating Hallucination Detection in LLMscited by 22
  12. 2025From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centeredcited by 21
38 more
  1. 2025Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigationcited by 20
  2. 2024Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measurecited by 18
  3. 2025Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Modelscited by 18
  4. 2025Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detectioncited by 18
  5. 2025Hallucination Detection in LLMs with Topological Divergence on Attention Graphscited by 18
  6. 2025Reconsidering LLM Uncertainty Estimation Methods in the Wildcited by 17
  7. 2025MUR: Momentum Uncertainty guided Reasoning for Large Language Modelscited by 17
  8. 2025CER: Confidence Enhanced Reasoning in LLMscited by 16
  9. 2025Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Modelscited by 16
  10. 2025MetaFaith: Faithful Natural Language Uncertainty Expression in LLMscited by 15
  11. 2025The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguitycited by 15
  12. 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunitiescited by 15
  13. 2024On Subjective Uncertainty Quantification and Calibration in Natural Language Generationcited by 14
  14. 2024UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Modelscited by 13
  15. 2024Training-Free Bayesianization for Low-Rank Adapters of Large Language Modelscited by 10
  16. 2025Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directionscited by 10
  17. 2024Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Modelscited by 9
  18. 2026Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantificationcited by 9
  19. 2024A Survey of Calibration Process for Black-Box LLMscited by 8
  20. 2025Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systemscited by 8
  21. 2025OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucinationcited by 8
  22. 2025Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAGcited by 8
  23. 2025Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generationcited by 7
  24. 2026BaseCal: Unsupervised Confidence Calibration via Base Model Signalscited by 7
  25. 2026Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volumecited by 7
  26. 2024FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guaranteescited by 6
  27. 2025Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Modelscited by 6
  28. 2025Estimating Semantic Alphabet Size for LLM Uncertainty Quantificationcited by 6
  29. 2025Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answeringcited by 6
  30. 2024Efficiently Deploying LLMs with Controlled Riskcited by 5
  31. 2025Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMscited by 5
  32. 2025Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Modelscited by 5
  33. 2026Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimizationcited by 5
  34. 2025Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropycited by 4
  35. 2025Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristicscited by 4
  36. 2025TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputscited by 4
  37. 2026Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Methodcited by 4
  38. 2026Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Studycited by 4

50 most cited of 156 All 156 (JSON)