mlsanityData to 14 Oct 2026

Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations

arXiv 2310.03951 ↗First posted 6 Oct 2023cs.CL cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in developing industry applications of LLMs. However, LLMs are prone to generate hallucinations that are not supported by the provided sources. In this paper, we propose a hierarchical framework to detect and mitigate such ungrounded hallucination. Our framework uses Chain of Natural Language Inference (CoNLI) for hallucination detection and hallucination reduction via post-editing. Our approach achieves state-of-the-art performance on hallucination detection and enhances text quality through rewrite, using LLMs without any fine-tuning or domain-specific prompt engineering. We show that this simple plug-and-play framework can serve as an effective choice for hallucination detection and reduction, achieving competitive performance across various contexts.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 6 Oct 2023.

Builds on

37 of 48 references.

References · 37

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  10. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  11. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  12. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
25 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  2. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  3. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  4. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  5. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  6. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  7. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  8. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 378
  9. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 376
  10. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  11. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
  12. 2023How Language Model Hallucinations Can Snowballcited by 311
  13. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 288
  14. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  15. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  16. 2023Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4cited by 202
  17. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 169
  18. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 152
  19. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 124
  20. 2020Evaluating Factuality in Generation with Dependency-level Entailmentcited by 122
  21. 2021Entity-level Factual Consistency of Abstractive Text Summarizationcited by 118
  22. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  23. 2019Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reportscited by 96
  24. 2023Why Does ChatGPT Fall Short in Providing Truthful Answers?cited by 54
  25. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarizationcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 21; 2025: 8; 2026: 5.

35 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  2. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  3. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 150
  4. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 49
  5. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  6. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  7. 2024Detecting Hallucinations in Large Language Model Generation: A Token Probability Approachcited by 42
  8. 2024Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detectorcited by 20
  9. 2024Constructing Benchmarks and Interventions for Combating Hallucinations in LLMscited by 19
  10. 2024SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Modelscited by 16
  11. 2024Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Modelscited by 15
  12. 2024ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Modelscited by 14
23 more
  1. 2024CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentationcited by 14
  2. 2025FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Datacited by 14
  3. 2025EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMscited by 10
  4. 2025CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generationcited by 9
  5. 2024Evaluating Consistency and Reasoning Capabilities of Large Language Modelscited by 7
  6. 2024ANAH: Analytical Annotation of Hallucinations in Large Language Modelscited by 7
  7. 2024Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learningcited by 7
  8. 2026Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Methodcited by 7
  9. 2024Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responsescited by 6
  10. 2024Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expressioncited by 6
  11. 2024SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detectioncited by 4
  12. 2025ConfRAG: Confidence-Guided Retrieval-Augmenting Generationcited by 4
  13. 2025TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputscited by 4
  14. 2024Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Promptingcited by 3
  15. 2024Design and evaluation of AI copilots -- case studies of retail copilot templatescited by 3
  16. 2024uMedSum: A Unified Framework for Advancing Medical Abstractive Summarizationcited by 3
  17. 2024Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Servicecited by 2
  18. 2026From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Modelscited by 2
  19. 2024MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-modelscited by 1
  20. 2025Deploying AI for Signal Processing education: Selected challenges and intriguing opportunitiescited by 1
  21. 2026Combating Spurious Correlations in Graph Interpretability via Self-Reflectioncited by 0
  22. 2026HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMscited by 0
  23. 2026Embedding Graph Kernel Entropy (EGKE): Fine-grained Hallucination Detection for LLMs from Embeddingscited by 0