mlsanityData to 7 Oct 2026

Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling

arXiv 2409.11283 ↗First posted 17 Sep 2024cs.CL cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections for text generation with open-ended answers are more challenging. Some researchers use external knowledge to detect hallucinations in generated texts, but external resources for specific scenarios are hard to access. Recent studies on detecting hallucinations in long text without external resources conduct consistency comparison among multiple sampled outputs. To handle long texts, researchers split long texts into multiple facts and individually compare the consistency of each pairs of facts. However, these methods (1) hardly achieve alignment among multiple facts; (2) overlook dependencies between multiple contextual facts. In this paper, we propose a graph-based context-aware (GCA) hallucination detection for text generations, which aligns knowledge facts and considers the dependencies between contextual knowledge triples in consistency comparison. Particularly, to align multiple facts, we conduct a triple-oriented response segmentation to extract multiple knowledge triples. To model dependencies among contextual knowledge triple (facts), we construct contextual triple into a graph and enhance triples' interactions via message passing and aggregating via RGCN. To avoid the omission of knowledge triples in long text, we conduct a LLM-based reverse verification via reconstructing the knowledge triples. Experiments show that our model enhances hallucination detection and excels all baselines.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 34 of its 55 references that are in the map. First posted on arXiv 17 Sep 2024.

Builds on

34 of 55 references.

References · 34

  1. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  2. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  3. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  4. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  5. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  6. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  7. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  8. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decodingcited by 198
  9. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 159
  10. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  11. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 98
  12. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 89
22 more
  1. 2023Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Modelscited by 67
  2. 2023On Early Detection of Hallucinations in Factual Question Answeringcited by 54
  3. 2023RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thoughtcited by 47
  4. 2023DelucionQA: Detecting Hallucinations in Domain-specific Question Answeringcited by 43
  5. 2024On Large Language Models' Hallucination with Regard to Known Factscited by 43
  6. 2023A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detectioncited by 42
  7. 2024DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detectioncited by 41
  8. 2024Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflectioncited by 40
  9. 2023Chainpoll: A high efficacy method for LLM hallucination detectioncited by 39
  10. 2023Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectificationcited by 38
  11. 2023FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledgecited by 24
  12. 2024Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answeringcited by 20
  13. 2024Large Language Models Struggle with Unreasonability in Math Problemscited by 18
  14. 2023GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidencecited by 14
  15. 2024PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamicscited by 14
  16. 2024Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinationscited by 12
  17. 2024Enabling Weak LLMs to Judge Response Reliability via Meta Rankingcited by 9
  18. 2023Reducing LLM Hallucinations using Epistemic Neural Networkscited by 8
  19. 2023Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classificationcited by 4
  20. 2023DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptationcited by 2
  21. 2024SHROOM-INDElab at SemEval-2024 Task 6: Zero- and Few-Shot LLM-Based Classification for Hallucination Detectioncited by 1
  22. 2024ERATTA: Extreme RAG for Table To Answers with Large Language Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 6.

9 papers.

  1. 2025Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Modelscited by 16
  2. 2025FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMscited by 14
  3. 2024The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal Statescited by 8
  4. 2026Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinationscited by 2
  5. 2026Temporal Graph Network: Hallucination Detection in Multi-Turn Conversationcited by 1
  6. 2026MedFabric: Gold Evidence Hides the Difficulty of Word-Level Medical Fabrication Detectioncited by 0
  7. 2026SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extractioncited by 0
  8. 2026MedHal-Loc: Are "Explainable-by-Architecture" Medical Hallucination Detectors Faithful Localizers? A Localization Benchmarkcited by 0
  9. 2026FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMscited by 0