mlsanityData to 7 Oct 2026

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

arXiv 2402.17811 ↗First posted 27 Feb 2024cs.CL cs.AI cs.LGcited by 90

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to fully unlocking LLM's knowledge potential. In this paper, we propose TruthX, an inference-time intervention method to activate the truthfulness of LLM by identifying and editing the features within LLM's internal representations that govern the truthfulness. TruthX employs an auto-encoder to map LLM's representations into semantic and truthful latent spaces respectively, and applies contrastive learning to identify a truthful editing direction within the truthful space. During inference, by editing LLM's internal representations in truthful space, TruthX effectively enhances the truthfulness of LLM. Experiments show that TruthX improves the truthfulness of 13 advanced LLMs by an average of 20% on TruthfulQA benchmark. Further analyses suggest that TruthX can control LLM to produce truthful or hallucinatory responses via editing only one vector in LLM's internal representations.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

30 of 43 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  6. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  7. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  8. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  9. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  10. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  11. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  12. 2020What Makes for Good Views for Contrastive Learning?cited by 843
18 more
  1. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 831
  2. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  3. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  4. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  5. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  6. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  7. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 598
  8. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 522
  9. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
  10. 2022Self-critiquing models for assisting human evaluatorscited by 372
  11. 2023Explainability for Large Language Models: A Surveycited by 331
  12. 2023Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Modelscited by 237
  13. 2023Inspecting and Editing Knowledge Representations in Language Modelscited by 140
  14. 2023Generating Benchmarks for Factuality Evaluation of Language Modelscited by 103
  15. 2023Alleviating Hallucinations of Large Language Models through Induced Hallucinationscited by 78
  16. 2023Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuningcited by 45
  17. 2023Second Thoughts are Best: Learning to Re-Align With Human Values from Text Editscited by 27
  18. 2024SH2: Self-Highlighted Hesitation Helps You Decode More Truthfullycited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 27; 2025: 42; 2026: 21.

90 papers.

Sort:

By area:

  1. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 140
  2. 2024Interpreting and Editing Vision-Language Representations to Mitigate Hallucinationscited by 103
  3. 2024Spectral Editing of Activations for Large Language Model Alignmentcited by 54
  4. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  5. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  6. 2025Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Modelscited by 38
  7. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  8. 2025A Survey on Mechanistic Interpretability for Multi-Modal Foundation Modelscited by 34
  9. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 30
  10. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  11. 2024PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restorationcited by 27
  12. 2024Mitigating Large Language Model Hallucination with Faithful Finetuningcited by 24
38 more
  1. 2024Can Editing LLMs Inject Harm?cited by 22
  2. 2026Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Modelscited by 22
  3. 2025Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysiscited by 20
  4. 2025Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigationcited by 20
  5. 2024Constructing Benchmarks and Interventions for Combating Hallucinations in LLMscited by 19
  6. 2024Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparatorscited by 19
  7. 2025Representation Engineering for Large-Language Models: Survey and Research Challengescited by 18
  8. 2024Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulnesscited by 17
  9. 2025KnowRL: Exploring Knowledgeable Reinforcement Learning for Factualitycited by 17
  10. 2025Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Modelscited by 16
  11. 2024Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contextscited by 15
  12. 2024Distinguishing Ignorance from Error in LLM Hallucinationscited by 14
  13. 2024Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Expertscited by 14
  14. 2025Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detectioncited by 13
  15. 2024FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMscited by 11
  16. 2024H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMscited by 11
  17. 2025Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generationcited by 10
  18. 2025Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safetycited by 10
  19. 2024NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Modelscited by 9
  20. 2024ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantationcited by 8
  21. 2024Integrative Decoding: Improve Factuality via Implicit Self-consistencycited by 8
  22. 2025Risk Assessment Framework for Code LLMs via Leveraging Internal Statescited by 8
  23. 2025Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancementcited by 8
  24. 2025Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoningcited by 8
  25. 2025Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Modelscited by 7
  26. 2025Evaluating Evaluation Metrics -- The Mirage of Hallucination Detectioncited by 6
  27. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 6
  28. 2025AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignmentcited by 6
  29. 2025HACK: Hallucinations Along Certainty and Knowledge Axescited by 6
  30. 2024Lens: Rethinking Multilingual Enhancement for Large Language Modelscited by 5
  31. 2025Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decodingcited by 5
  32. 2025Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptationcited by 5
  33. 2025Large Language Model Sourcing: A Surveycited by 5
  34. 2024Selected Languages are All You Need for Cross-lingual Truthfulness Transfercited by 4
  35. 2024Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucinationcited by 4
  36. 2025Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wildcited by 4
  37. 2025LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signalscited by 4
  38. 2025REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Modelcited by 4

50 most cited of 90 All 90 (JSON)