mlsanityData to 7 Oct 2026

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs

arXiv 2406.15927 ↗First posted 22 Jun 2024cs.CL cs.AI cs.LGcited by 246

Not on the map. Why?

Cited by 36 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose semantic entropy probes (SEPs), a cheap and reliable method for uncertainty quantification in Large Language Models (LLMs). Hallucinations, which are plausible-sounding but factually incorrect and arbitrary model generations, present a major challenge to the practical adoption of LLMs. Recent work by Farquhar et al. (2024) proposes semantic entropy (SE), which can detect hallucinations by estimating uncertainty in the space semantic meaning for a set of model generations. However, the 5-to-10-fold increase in computation cost associated with SE computation hinders practical adoption. To address this, we propose SEPs, which directly approximate SE from the hidden states of a single generation. SEPs are simple to train and do not require sampling multiple model generations at test time, reducing the overhead of semantic uncertainty quantification to almost zero. We show that SEPs retain high performance for hallucination detection and generalize better to out-of-distribution data than previous probing methods that directly predict model accuracy. Our results across models and tasks suggest that model hidden states capture SE, and our ablation studies give further insights into the token positions and model layers for which this is the case.

Key facts. Cited by 246 papers in the map (data through 7 Oct 2026). Builds on 57 of its 75 references that are in the map. First posted on arXiv 22 Jun 2024.

Builds on

57 of 75 references.

References · 57

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2019Language Models as Knowledge Bases?cited by 1,922
  8. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  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. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  12. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
38 more
  1. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  2. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  3. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  4. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,009
  5. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  6. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 831
  7. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  8. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  9. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  10. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  11. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  12. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  13. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  14. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  15. 2023Eliciting Latent Predictions from Transformers with the Tuned Lenscited by 579
  16. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  17. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  18. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  19. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  20. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  21. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  22. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  23. 2023Fine-tuning Language Models for Factualitycited by 219
  24. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 217
  25. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  26. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  27. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  28. 2021Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarizationcited by 128
  29. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 123
  30. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  31. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 121
  32. 2018Correcting Length Bias in Neural Machine Translationcited by 119
  33. 2023Future Lens: Anticipating Subsequent Tokens from a Single Hidden Statecited by 116
  34. 2023Do Language Models Know When They're Hallucinating References?cited by 115
  35. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  36. 2020Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summarycited by 87
  37. 2020Controlled Hallucinations: Learning to Generate Faithfully from Noisy Datacited by 83
  38. 2023Selectively Answering Ambiguous Questionscited by 63

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 19; 2025: 85; 2026: 142.

246 papers.

Sort:

By area:

  1. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
  2. 2024Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Modelscited by 114
  3. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 100
  4. 2025SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimizationcited by 87
  5. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 74
  6. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 62
  7. 2024Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Modelscited by 55
  8. 2025Steer LLM Latents for Hallucination Detectioncited by 49
  9. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  10. 2025Hallucination Detection in LLMs Using Spectral Features of Attention Mapscited by 42
  11. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  12. 2025Real-Time Detection of Hallucinated Entities in Long-Form Generationcited by 33
38 more
  1. 2025Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lenscited by 32
  2. 2025ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMscited by 31
  3. 2025Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistencycited by 30
  4. 2025A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcarecited by 27
  5. 2025Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answercited by 26
  6. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  7. 2025Revisiting Uncertainty Estimation and Calibration of Large Language Modelscited by 22
  8. 2025The Illusion of Progress: Re-evaluating Hallucination Detection in LLMscited by 22
  9. 2024A Survey on the Honesty of Large Language Modelscited by 21
  10. 2025Uncertainty-Aware Step-wise Verification with Generative Reward Modelscited by 21
  11. 2025Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMscited by 19
  12. 2025Robust Hallucination Detection in LLMs via Adaptive Token Selectioncited by 19
  13. 2024Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measurecited by 18
  14. 2024On the Limitations of Compute Thresholds as a Governance Strategycited by 17
  15. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagationcited by 17
  16. 2025Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorerscited by 16
  17. 2025Trace Length is a Simple Uncertainty Signal in Reasoning Modelscited by 16
  18. 2025Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputscited by 15
  19. 2025FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMscited by 14
  20. 2025Depth Gives a False Sense of Privacy: LLM Internal States Inversioncited by 14
  21. 2025Enhancing Hallucination Detection through Noise Injectioncited by 13
  22. 2025Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detectioncited by 13
  23. 2026Knowing When to Abstain: Medical LLMs Under Clinical Uncertaintycited by 13
  24. 2026DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learningcited by 13
  25. 2025Query-Level Uncertainty in Large Language Modelscited by 12
  26. 2025Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMscited by 12
  27. 2025Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generationcited by 10
  28. 2025Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMscited by 10
  29. 2025Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directionscited by 10
  30. 2024Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropycited by 9
  31. 2025Rational Tuning of LLM Cascades via Probabilistic Modelingcited by 9
  32. 2025Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervisioncited by 9
  33. 2025SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMscited by 9
  34. 2025The Geometries of Truth Are Orthogonal Across Taskscited by 9
  35. 2025Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Ratecited by 9
  36. 2026Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantificationcited by 9
  37. 2024Integrative Decoding: Improve Factuality via Implicit Self-consistencycited by 8
  38. 2025Estimating LLM Consistency: A User Baseline vs Surrogate Metricscited by 8

50 most cited of 246 All 246 (JSON)