mlsanityData to 14 Oct 2026

NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning

arXiv 2606.13171 ↗First posted 11 Jun 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Hallucination detection and mitigation

Abstract (arXiv)

The rapid updates of online news make tracking event developments challenging, highlighting the need for timeline summarization (TLS). Hallucinations, where LLM-generated content deviates from source news, still remain a critical issue in LLM-based TLS and are not well studied in existing works. To bridge this gap, we identify two primary types of hallucinations: unfaithful content during news summarization and information omission in date-event summarization. Then, we propose NTS-CoT, a novel framework that leverages Chain-of-Thought (CoT) reasoning to mitigate hallucinations in TLS. The framework consists of three key modules: i) Element-CoT to capture essential news elements for faithful summarization, ii) Date Selection to combine temporal saliency and event prominence for timestamp selection, and iii) Causal-CoT to infer causal relationships and reduce omissions in date-event summarization. Extensive experiments, including quantitative analysis on three TLS benchmarks and human evaluation, demonstrate that NTS-CoT outperforms state-of-the-art baselines, effectively mitigating hallucinations and improving LLM-based TLS performance. Our source code is available at https://anonymous.4open.science/r/NTS-CoT .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 35 of its 56 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

35 of 56 references.

References · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  9. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  10. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  11. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  12. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
23 more
  1. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  2. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  3. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  4. 2023R-Tuning: Instructing Large Language Models to Say `I Don't Know'cited by 111
  5. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 92
  6. 2023Alleviating Hallucinations of Large Language Models through Induced Hallucinationscited by 79
  7. 2023Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Methodcited by 76
  8. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 72
  9. 2022Mutual Information Alleviates Hallucinations in Abstractive Summarizationcited by 68
  10. 2023Extractive Summarization via ChatGPT for Faithful Summary Generationcited by 59
  11. 2023Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Modelscited by 31
  12. 2020Examining the State-of-the-Art in News Timeline Summarizationcited by 27
  13. 2018A Temporally Sensitive Submodularity Framework for Timeline Summarizationcited by 17
  14. 2023"Why is this misleading?": Detecting News Headline Hallucinations with Explanationscited by 17
  15. 2024Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistencycited by 14
  16. 2025Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarizationcited by 13
  17. 2024Combining Hierachical VAEs with LLMs for clinically meaningful timeline summarisation in social mediacited by 8
  18. 2024Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevancecited by 7
  19. 2023Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Ordercited by 6
  20. 2024Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Informationcited by 6
  21. 2024AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preferencecited by 4
  22. 2023Named Entity Inclusion in Abstractive Text Summarizationcited by 3
  23. 2023Web News Timeline Generation with Extended Task Promptingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Models
  2. 2024Temporal reasoning for timeline summarisation in social media
  3. 2023Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models
  4. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization
  5. 2025Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
  6. 2024Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models
  7. 2024FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
  8. 2025HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation