mlsanityData to 7 Oct 2026

Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis

arXiv 2502.08663 ↗First posted 10 Feb 2025cs.CL cs.AI cs.CYcited by 5

Not on the map. Why?

Abstract (arXiv)

Hallucinations are one of the major issues affecting LLMs, hindering their wide adoption in production systems. While current research solutions for detecting hallucinations are mainly based on heuristics, in this paper we introduce a mathematically sound methodology to reason about hallucination, and leverage it to build a tool to detect hallucinations. To the best of our knowledge, we are the first to show that hallucinated content has structural differences with respect to correct content. To prove this result, we resort to the Minkowski distances in the embedding space. Our findings demonstrate statistically significant differences in the embedding distance distributions, that are also scale free -- they qualitatively hold regardless of the distance norm used and the number of keywords, questions, or responses. We leverage these structural differences to develop a tool to detect hallucinated responses, achieving an accuracy of 66% for a specific configuration of system parameters -- comparable with the best results in the field. In conclusion, the suggested methodology is promising and novel, possibly paving the way for further research in the domain, also along the directions highlighted in our future work.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

33 of 49 references.

References · 33

  1. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  2. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  6. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  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. 2020SummEval: Re-evaluating Summarization Evaluationcited by 666
  12. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
21 more
  1. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  2. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  3. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  4. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 230
  5. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  6. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  7. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 137
  8. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 96
  9. 2020Controlled Hallucinations: Learning to Generate Faithfully from Noisy Datacited by 83
  10. 2022Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translationcited by 60
  11. 2021Score-Based Generative Classifierscited by 53
  12. 2023Nationality Bias in Text Generationcited by 50
  13. 2023Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Modelscited by 40
  14. 2023Chainpoll: A high efficacy method for LLM hallucination detectioncited by 39
  15. 2023Trapping LLM Hallucinations Using Tagged Context Promptscited by 34
  16. 2024Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targetscited by 31
  17. 2021On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributionscited by 22
  18. 2024Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluationcited by 15
  19. 2023Reducing LLM Hallucinations using Epistemic Neural Networkscited by 8
  20. 2024The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal Statescited by 8
  21. 2022Fast O_{expected}(N) Algorithm for Finding Exact Maximum Distance in E^2 Instead of O(N^2) or O(N lg N)cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generationcited by 1
  2. 2025PRISM: Phase-enhanced Radial-based Image Signature Mapping framework for fingerprinting AI-generated imagescited by 0
  3. 2025The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systemscited by 0
  4. 2026Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurementcited by 0
  5. 2026ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Languagecited by 0