mlsanityData to 7 Oct 2026

INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection

arXiv 2402.03744 ↗First posted 6 Feb 2024cs.CLcited by 317

Not on the map. Why?

Cited by 38 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs. Previous efforts in detecting hallucinations have been employed at logit-level uncertainty estimation or language-level self-consistency evaluation, where the semantic information is inevitably lost during the token-decoding procedure. Thus, we propose to explore the dense semantic information retained within LLMs' INternal States for hallucInation DEtection (INSIDE). In particular, a simple yet effective EigenScore metric is proposed to better evaluate responses' self-consistency, which exploits the eigenvalues of responses' covariance matrix to measure the semantic consistency/diversity in the dense embedding space. Furthermore, from the perspective of self-consistent hallucination detection, a test time feature clipping approach is explored to truncate extreme activations in the internal states, which reduces overconfident generations and potentially benefits the detection of overconfident hallucinations. Extensive experiments and ablation studies are performed on several popular LLMs and question-answering (QA) benchmarks, showing the effectiveness of our proposal.

Key facts. Cited by 317 papers in the map (data through 7 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

30 of 46 references.

References · 30

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  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. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  11. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  12. 2022Language Models (Mostly) Know What They Knowcited by 1,783
18 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  2. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  3. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  4. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  5. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  6. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  7. 2018CoQA: A Conversational Question Answering Challengecited by 674
  8. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  11. 2023Do Large Language Models Know What They Don't Know?cited by 238
  12. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  13. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  14. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  15. 2022Natural Language to Code Translation with Executioncited by 122
  16. 2023Semantic Consistency for Assuring Reliability of Large Language Modelscited by 15
  17. 2021Understanding Neural Networks with Logarithm Determinant Entropy Estimatorcited by 10
  18. 2024Optimal Parameter and Neuron Pruning for Out-of-Distribution Detectioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 52; 2025: 118; 2026: 147.

317 papers.

Sort:

By area:

  1. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 230
  2. 2024To Believe or Not to Believe Your LLMcited by 120
  3. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  4. 2024Interpreting and Editing Vision-Language Representations to Mitigate Hallucinationscited by 103
  5. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 100
  6. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 96
  7. 2024MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationcited by 87
  8. 2024A Primer on the Inner Workings of Transformer-based Language Modelscited by 83
  9. 2024LLM Internal States Reveal Hallucination Risk Faced With a Querycited by 80
  10. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 74
  11. 2024Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approachcited by 73
  12. 2025A Survey of Uncertainty Estimation Methods on Large Language Modelscited by 57
38 more
  1. 2024Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluationcited by 56
  2. 2025HaluMem: Evaluating Hallucinations in Memory Systems of Agentscited by 51
  3. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  4. 2025Steer LLM Latents for Hallucination Detectioncited by 49
  5. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  6. 2025Hallucination Detection in LLMs Using Spectral Features of Attention Mapscited by 42
  7. 2024Uncertainty in Language Models: Assessment through Rank-Calibrationcited by 40
  8. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
  9. 2025A Unified Understanding and Evaluation of Steering Methodscited by 40
  10. 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Makingcited by 36
  11. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Modelscited by 35
  12. 2024Improving Uncertainty Estimation through Semantically Diverse Language Generationcited by 34
  13. 2025Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspectivecited by 32
  14. 2025Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistencycited by 30
  15. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  16. 2024Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Taskscited by 24
  17. 2025Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancementcited by 24
  18. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  19. 2024Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMscited by 23
  20. 2025The Illusion of Progress: Re-evaluating Hallucination Detection in LLMscited by 22
  21. 2024A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagationcited by 21
  22. 2024A Survey on the Honesty of Large Language Modelscited by 21
  23. 2025Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Resultscited by 21
  24. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluationcited by 20
  25. 2024Constructing Benchmarks and Interventions for Combating Hallucinations in LLMscited by 19
  26. 2025Robust Hallucination Detection in LLMs via Adaptive Token Selectioncited by 19
  27. 2024A Causal Explainable Guardrails for Large Language Modelscited by 18
  28. 2024Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measurecited by 18
  29. 2025Representation Engineering for Large-Language Models: Survey and Research Challengescited by 18
  30. 2025Hallucination Detection in LLMs with Topological Divergence on Attention Graphscited by 18
  31. 2025Too Consistent to Detect: A Study of Self-Consistent Errors in LLMscited by 18
  32. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagationcited by 17
  33. 2024VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wildcited by 17
  34. 2025Correctness Assessment of Code Generated by Large Language Models Using Internal Representationscited by 17
  35. 2025Reconsidering LLM Uncertainty Estimation Methods in the Wildcited by 17
  36. 2025Probing for Arithmetic Errors in Language Modelscited by 17
  37. 2025MUR: Momentum Uncertainty guided Reasoning for Large Language Modelscited by 17
  38. 2024AcTracer: Active Testing of Large Language Model via Multi-Stage Samplingcited by 16

50 most cited of 317 All 317 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Theoretical Foundations and Mitigation of Hallucination in Large Language Models
  2. 2025Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection
  3. 2026External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
  4. 2026BEACON: Behavioral Entropy Aggregation for Cross-Model Hallucination Detection in Large Language Models
  5. 2026Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights
  6. 2025MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs
  7. 2026UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space
  8. 2025The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems