v1v2v3 (latest)

Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization

21 May 2025

ArXiv (abs)PDF HTML Github (67466★)

Papers citing "Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization"

5 / 5 papers shown

The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers

222

13 Oct 2025

Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection

Atharva Kulkarni

Yuan-kang Zhang

Joel Ruben Antony Moniz

383

25 Apr 2025

Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided DecodingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024

454

20 Feb 2025

Learning to Summarize from LLM-generated FeedbackNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024

367

28 Jan 2025

AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric KnowledgeNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024

475

11 Sep 2024