mlsanityData to 7 Oct 2026

SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency

arXiv 2311.01740 ↗First posted 3 Nov 2023cs.CLcited by 89

Not on the map. Why?

Abstract (arXiv)

Hallucination detection is a critical step toward understanding the trustworthiness of modern language models (LMs). To achieve this goal, we re-examine existing detection approaches based on the self-consistency of LMs and uncover two types of hallucinations resulting from 1) question-level and 2) model-level, which cannot be effectively identified through self-consistency check alone. Building upon this discovery, we propose a novel sampling-based method, i.e., semantic-aware cross-check consistency (SAC3) that expands on the principle of self-consistency checking. Our SAC3 approach incorporates additional mechanisms to detect both question-level and model-level hallucinations by leveraging advances including semantically equivalent question perturbation and cross-model response consistency checking. Through extensive and systematic empirical analysis, we demonstrate that SAC3 outperforms the state of the art in detecting both non-factual and factual statements across multiple question-answering and open-domain generation benchmarks.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 3 Nov 2023.

Builds on

26 of 40 references.

References · 26

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  7. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  8. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  9. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 755
  10. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  11. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 361
  12. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
14 more
  1. 2023How Language Model Hallucinations Can Snowballcited by 310
  2. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  3. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  4. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
  5. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 137
  6. 2021Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarizationcited by 128
  7. 2023Do Language Models Know When They're Hallucinating References?cited by 115
  8. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 90
  9. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 82
  10. 2023Why Does ChatGPT Fall Short in Providing Truthful Answers?cited by 54
  11. 2022RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Groundingcited by 47
  12. 2023A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detectioncited by 42
  13. 2023Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMscited by 36
  14. 2023Diving Deep into Modes of Fact Hallucinations in Dialogue Systemscited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 28; 2025: 34; 2026: 24.

89 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  3. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 253
  4. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
  5. 2024To Believe or Not to Believe Your LLMcited by 120
  6. 2023Alleviating Hallucinations of Large Language Models through Induced Hallucinationscited by 78
  7. 2024A Survey of Uncertainty Estimation in LLMs: Theory Meets Practicecited by 54
  8. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  9. 2024Multicalibration for Confidence Scoring in LLMscited by 44
  10. 2024Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflectioncited by 40
  11. 2025Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physicscited by 33
  12. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMscited by 27
38 more
  1. 2025Estimating LLM Uncertainty with Evidencecited by 26
  2. 2024RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Modelscited by 24
  3. 2024Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMscited by 23
  4. 2024Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Frameworkcited by 19
  5. 2025Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detectioncited by 18
  6. 2025Too Consistent to Detect: A Study of Self-Consistent Errors in LLMscited by 18
  7. 2024The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Modelscited by 17
  8. 2024An Audit on the Perspectives and Challenges of Hallucinations in NLPcited by 17
  9. 2025Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Modelscited by 16
  10. 2025CER: Confidence Enhanced Reasoning in LLMscited by 16
  11. 2024DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Modelscited by 15
  12. 2026AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agentscited by 15
  13. 2024On Subjective Uncertainty Quantification and Calibration in Natural Language Generationcited by 14
  14. 2024Improving Weak-to-Strong Generalization with Reliability-Aware Alignmentcited by 14
  15. 2025Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoningcited by 14
  16. 2025LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilizationcited by 11
  17. 2024FACTOID: FACtual enTailment fOr hallucInation Detectioncited by 10
  18. 2024CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Taskscited by 10
  19. 2024Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filteringcited by 10
  20. 2024Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modelingcited by 9
  21. 2024Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domaincited by 9
  22. 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Taskscited by 9
  23. 2024A Survey of Calibration Process for Black-Box LLMscited by 8
  24. 2025Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detectioncited by 8
  25. 2024A Survey of Automatic Hallucination Evaluation on Natural Language Generationcited by 7
  26. 2025Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Modelscited by 7
  27. 2025Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulnesscited by 7
  28. 2024DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluationcited by 6
  29. 2025A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithmcited by 6
  30. 2025Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularitycited by 6
  31. 2025Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Modelscited by 6
  32. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 6
  33. 2026The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillationcited by 6
  34. 2024Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answeringcited by 5
  35. 2025UniVRSE: Unified Vision-conditioned Response Semantic Entropy for Hallucination Detection in Medical Vision-Language Modelscited by 5
  36. 2025D2HScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMscited by 5
  37. 2024DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Modelscited by 4
  38. 2024CLUE: Concept-Level Uncertainty Estimation for Large Language Modelscited by 4

50 most cited of 89 All 89 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SelfCheck-Eval: A Multi-Module Framework for Zero-Resource Hallucination Detection in Large Language Models
  2. 2026Zero-source LLM Hallucination Detection with Human-like Criteria Probing
  3. 2025Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations
  4. 2025Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
  5. 2026Domain-Specific Hallucination Detection in Large Language Models
  6. 2025Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models
  7. 2026AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models
  8. 2026The First Token Knows: Single-Decode Confidence for Hallucination Detection