mlsanityData to 7 Oct 2026

Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension

arXiv 2402.18048 ↗First posted 28 Feb 2024cs.CLcited by 45

Not on the map. Why?

Abstract (arXiv)

We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs), which serves as a crucial step in building trust between humans and LLMs. Although several approaches based on entropy or verbalized uncertainty have been proposed to calibrate model predictions, these methods are often intractable, sensitive to hyperparameters, and less reliable when applied in generative tasks with LLMs. In this paper, we suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations. Through experiments on four question answering (QA) datasets, we demonstrate the effectiveness ohttps://info.arxiv.org/help/prep#abstractsf our proposed method. Additionally, we study intrinsic dimensions in LLMs and their relations with model layers, autoregressive language modeling, and the training of LLMs, revealing that intrinsic dimensions can be a powerful approach to understanding LLMs.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

31 of 44 references.

References · 31

  1. 2023GPT-4 Technical Reportcited by 18,132
  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. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  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. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
19 more
  1. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  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. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  5. 2018CoQA: A Conversational Question Answering Challengecited by 674
  6. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  7. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  8. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
  9. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
  10. 2021Unsolved Problems in ML Safetycited by 291
  11. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  12. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  13. 2019Intrinsic dimension of data representations in deep neural networkscited by 276
  14. 2018Estimating the intrinsic dimension of datasets by a minimal neighborhood informationcited by 246
  15. 2020Selective Question Answering under Domain Shiftcited by 228
  16. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  17. 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Textscited by 111
  18. 2021Intrinsic Dimension, Persistent Homology and Generalization in Neural Networkscited by 70
  19. 2019Geometry-Aware Maximum Likelihood Estimation of Intrinsic Dimensioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 24; 2026: 11.

45 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. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 96
  4. 2024ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guaranteescited by 62
  5. 2024Emergence of a High-Dimensional Abstraction Phase in Language Transformerscited by 56
  6. 2025Steer LLM Latents for Hallucination Detectioncited by 49
  7. 2025A Unified Understanding and Evaluation of Steering Methodscited by 40
  8. 2024Safety-Aware Fine-Tuning of Large Language Modelscited by 33
  9. 2024Constructing Benchmarks and Interventions for Combating Hallucinations in LLMscited by 19
  10. 2025Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detectioncited by 18
  11. 2025Representation Engineering for Large-Language Models: Survey and Research Challengescited by 18
  12. 2025Correctness Assessment of Code Generated by Large Language Models Using Internal Representationscited by 17
33 more
  1. 2025Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViTcited by 16
  2. 2024Distinguishing Ignorance from Error in LLM Hallucinationscited by 14
  3. 2025Generative Modeling of Weights: Generalization or Memorization?cited by 12
  4. 2025Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributionscited by 11
  5. 2025Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviorscited by 11
  6. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalizationcited by 9
  7. 2025Geometry of Decision Making in Language Modelscited by 8
  8. 2025A quantitative analysis of semantic information in deep representations of text and imagescited by 7
  9. 2024Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generationcited by 6
  10. 2025Aligning Large Language Models for Faithful Integrity Against Opposing Argumentcited by 6
  11. 2026Differential syntactic and semantic encoding in LLMscited by 6
  12. 2025Neural Message-Passing on Attention Graphs for Hallucination Detectioncited by 5
  13. 2025Geometric Metrics and LLMs: What They Measure and When They Workcited by 4
  14. 2025A Connection Between Score Matching and Local Intrinsic Dimensioncited by 4
  15. 2026The Confidence Manifold: Geometric Structure of Correctness Representations in Language Modelscited by 4
  16. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
  17. 2025ConfRAG: Confidence-Guided Retrieval-Augmenting Generationcited by 3
  18. 2026Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representationscited by 3
  19. 2026CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networkscited by 3
  20. 2026Automatic Layer Selection for Hallucination Detectioncited by 3
  21. 2025Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinationscited by 2
  22. 2024A Comparative Study of Learning Paradigms in Large Language Models via Intrinsic Dimensioncited by 1
  23. 2025Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimensioncited by 1
  24. 2025The Rise of Parameter Specialization for Knowledge Storage in Large Language Modelscited by 1
  25. 2025Geometric Analysis of Neural Regression Collapse via Intrinsic Dimensioncited by 1
  26. 2025Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Storycited by 1
  27. 2025The Right to Be Remembered: Preserving Maximally Truthful Digital Memory in the Age of AIcited by 0
  28. 2026What do Geometric Hallucination Detection Metrics Actually Measure?cited by 0
  29. 2026Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Modelscited by 0
  30. 2026FLaG: Fine-Grained Latent Grouping for Hallucination Detectioncited by 0
  31. 2026How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Modelscited by 0
  32. 2026Local Sparsity Enables Unsupervised LLM Safety Detectioncited by 0
  33. 2026Toward a Graded Measure of Belief Stability in Large Language Modelscited by 0