mlsanityData to 7 Oct 2026

Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach

arXiv 2405.19648 ↗First posted 30 May 2024cs.CL cs.AI cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated content. Current methods often demand substantial resources and rely on extensive LLMs or employ supervised learning with multidimensional features or intricate linguistic and semantic analyses difficult to reproduce and largely depend on using the same LLM that hallucinated. This paper introduces a supervised learning approach employing two simple classifiers utilizing only four numerical features derived from tokens and vocabulary probabilities obtained from other LLM evaluators, which are not necessarily the same. The method yields promising results, surpassing state-of-the-art outcomes in multiple tasks across three different benchmarks. Additionally, we provide a comprehensive examination of the strengths and weaknesses of our approach, highlighting the significance of the features utilized and the LLM employed as an evaluator. We have released our code publicly at https://github.com/Baylor-AI/HalluDetect.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

28 of 37 references.

References · 28

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  6. 2020Longformer: The Long-Document Transformercited by 3,362
  7. 2016Pointer Sentinel Mixture Modelscited by 2,992
  8. 2023A Survey of Large Language Modelscited by 2,537
  9. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  10. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  11. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  12. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
16 more
  1. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  3. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  4. 2023GPTScore: Evaluate as You Desirecited by 357
  5. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  6. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  7. 2023Challenges and Applications of Large Language Modelscited by 251
  8. 2023Do Large Language Models Know What They Don't Know?cited by 238
  9. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  10. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  11. 2023Are Emergent Abilities in Large Language Models just In-Context Learning?cited by 109
  12. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 87
  13. 2024Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Modelscited by 84
  14. 2023Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinationscited by 34
  15. 2023Diving Deep into Modes of Fact Hallucinations in Dialogue Systemscited by 32
  16. 2023Mini-DALLE3: Interactive Text to Image by Prompting Large Language Modelscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 19; 2026: 14.

40 papers.

Sort:

By area:

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  2. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluationcited by 20
  3. 2025Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMscited by 19
  4. 2025Robust Hallucination Detection in LLMs via Adaptive Token Selectioncited by 19
  5. 2024Quantized Delta Weight Is Safety Keepercited by 12
  6. 2025Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMscited by 12
  7. 2025Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Ratecited by 9
  8. 2024FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formatscited by 8
  9. 2024Prompt-Guided Internal States for Hallucination Detection of Large Language Modelscited by 8
  10. 2025HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMscited by 8
  11. 2026HALT: Hallucination Assessment via Log-probs as Time seriescited by 8
  12. 2025Span-Level Hallucination Detection for LLM-Generated Answerscited by 5
28 more
  1. 2026MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probingcited by 5
  2. 2025First Hallucination Tokens Are Different from Conditional Onescited by 4
  3. 2026Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Methodcited by 4
  4. 2024Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropycited by 3
  5. 2024Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbotscited by 3
  6. 2026Entropy-Tree: Tree-Based Decoding with Entropy-Guided Explorationcited by 3
  7. 2026Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Predictioncited by 3
  8. 2024Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Servicecited by 2
  9. 2024Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledgecited by 2
  10. 2025What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysiscited by 2
  11. 2025From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Modelscited by 2
  12. 2026PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Lengthcited by 2
  13. 2025Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitorcited by 1
  14. 2025From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errorscited by 1
  15. 2025Leveraging NTPs for Efficient Hallucination Detection in VLMscited by 1
  16. 2025HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzingcited by 1
  17. 2025Teaming LLMs to Detect and Mitigate Hallucinationscited by 1
  18. 2026FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answeringcited by 1
  19. 2026"I May Not Have Articulated Myself Clearly": Diagnosing Dynamic Instability in LLM Reasoning at Inference Timecited by 1
  20. 2026Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scalingcited by 1
  21. 2026The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judgecited by 1
  22. 2026Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debatecited by 1
  23. 2026Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carriercited by 1
  24. 2026What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamicscited by 1
  25. 2025AILS-NTUA at SemEval-2025 Task 3: Leveraging Large Language Models and Translation Strategies for Multilingual Hallucination Detectioncited by 0
  26. 2025When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoringcited by 0
  27. 2025Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Modelscited by 0
  28. 2026Grad Detect: Gradient-Based Hallucination Detection in LLMscited by 0