mlsanityData to 7 Oct 2026

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection

arXiv 2409.17504 ↗First posted 26 Sep 2024cs.LG cs.CLcited by 96

Not on the map. Why?

Abstract (arXiv)

The surge in applications of large language models (LLMs) has prompted concerns about the generation of misleading or fabricated information, known as hallucinations. Therefore, detecting hallucinations has become critical to maintaining trust in LLM-generated content. A primary challenge in learning a truthfulness classifier is the lack of a large amount of labeled truthful and hallucinated data. To address the challenge, we introduce HaloScope, a novel learning framework that leverages the unlabeled LLM generations in the wild for hallucination detection. Such unlabeled data arises freely upon deploying LLMs in the open world, and consists of both truthful and hallucinated information. To harness the unlabeled data, we present an automated membership estimation score for distinguishing between truthful and untruthful generations within unlabeled mixture data, thereby enabling the training of a binary truthfulness classifier on top. Importantly, our framework does not require extra data collection and human annotations, offering strong flexibility and practicality for real-world applications. Extensive experiments show that HaloScope can achieve superior hallucination detection performance, outperforming the competitive rivals by a significant margin. Code is available at https://github.com/deeplearningwisc/haloscope.

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Builds on 47 of its 55 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

47 of 55 references.

References · 47

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  9. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  10. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  11. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  12. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
35 more
  1. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  2. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  3. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  4. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  5. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  6. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  7. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  8. 2018CoQA: A Conversational Question Answering Challengecited by 674
  9. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  10. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
  11. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 367
  12. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  13. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 329
  14. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  15. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  16. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  17. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  18. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  19. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  20. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  21. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 123
  22. 2023Do Language Models Know When They're Hallucinating References?cited by 115
  23. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 98
  24. 2024Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Modelscited by 84
  25. 2023Alleviating Hallucinations of Large Language Models through Induced Hallucinationscited by 78
  26. 2023Self-Evaluation Improves Selective Generation in Large Language Modelscited by 74
  27. 2019Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generationcited by 62
  28. 2022Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translationcited by 60
  29. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  30. 2024Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden Statescited by 50
  31. 2024Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimensioncited by 45
  32. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  33. 2023Weakly Supervised Detection of Hallucinations in LLM Activationscited by 20
  34. 2024SH2: Self-Highlighted Hesitation Helps You Decode More Truthfullycited by 15
  35. 2024Out-of-Distribution Learning with Human Feedbackcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 45; 2026: 47.

96 papers.

Sort:

By area:

  1. 2024Process Reward Model with Q-Value Rankingscited by 78
  2. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 74
  3. 2025Steer LLM Latents for Hallucination Detectioncited by 49
  4. 2025A Unified Understanding and Evaluation of Steering Methodscited by 40
  5. 2024Safety-Aware Fine-Tuning of Large Language Modelscited by 33
  6. 2025Robust Hallucination Detection in LLMs via Adaptive Token Selectioncited by 19
  7. 2025Too Consistent to Detect: A Study of Self-Consistent Errors in LLMscited by 18
  8. 2024VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wildcited by 17
  9. 2025HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detectioncited by 13
  10. 2025HalluciNot: Hallucination Detection Through Context and Common Knowledge Verificationcited by 13
  11. 2025Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Modelscited by 12
  12. 2025TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Interventioncited by 11
38 more
  1. 2025Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviorscited by 11
  2. 2025GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similaritycited by 11
  3. 2025Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directionscited by 10
  4. 2025HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMscited by 8
  5. 2025TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Modelscited by 7
  6. 2025Hallucination Benchmark for Speech Foundation Modelscited by 7
  7. 2026TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphscited by 7
  8. 2024MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Modelscited by 6
  9. 2025Evaluating Evaluation Metrics -- The Mirage of Hallucination Detectioncited by 6
  10. 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoringcited by 6
  11. 2025Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysiscited by 5
  12. 2025EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistantscited by 5
  13. 2026Confundo: Learning to Generate Robust Poison for Practical RAG Systemscited by 5
  14. 2025Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generationcited by 4
  15. 2025Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalizationcited by 4
  16. 2025ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoningcited by 4
  17. 2025Probing Neural Topology of Large Language Modelscited by 4
  18. 2025Cross-Layer Attention Probing for Fine-Grained Hallucination Detectioncited by 4
  19. 2025HARP: Hallucination Detection via Reasoning Subspace Projectioncited by 4
  20. 2025LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signalscited by 4
  21. 2025Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimationcited by 4
  22. 2025HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMscited by 4
  23. 2026The Confidence Manifold: Geometric Structure of Correctness Representations in Language Modelscited by 4
  24. 2025RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detectioncited by 3
  25. 2025Revealing Multimodal Causality with Large Language Modelscited by 3
  26. 2025MASH: Modeling Abstention via Selective Help-Seekingcited by 3
  27. 2025ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representationscited by 3
  28. 2026Lyapunov Probes for Hallucination Detection in Large Foundation Modelscited by 3
  29. 2026HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoderscited by 3
  30. 2026PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifactscited by 3
  31. 2025Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinationscited by 2
  32. 2025AgriDoctor: A Multimodal Intelligent Assistant for Agriculturecited by 2
  33. 2025Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Datacited by 2
  34. 2026HalluZig: Hallucination Detection using Zigzag Persistencecited by 2
  35. 2026LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queriescited by 2
  36. 2026Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?cited by 2
  37. 2026SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplificationcited by 2
  38. 2026How Retrieved Context Shapes Internal Representations in RAGcited by 2

50 most cited of 96 All 96 (JSON)