mlsanityData to 7 Oct 2026

A Concise Review of Hallucinations in LLMs and their Mitigation

arXiv 2512.02527 ↗First posted 2 Dec 2025cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Traditional language models face a challenge from hallucinations. Their very presence casts a large, dangerous shadow over the promising realm of natural language processing. It becomes crucial to understand the various kinds of hallucinations that occur nowadays, their origins, and ways of reducing them. This document provides a concise and straightforward summary of that. It serves as a one-stop resource for a general understanding of hallucinations and how to mitigate them.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 2 Dec 2025.

Builds on

14 of 24 references.

References · 14

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  3. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  4. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  5. 2024Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?cited by 227
  6. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 123
  7. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 96
  8. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  9. 2023On Early Detection of Hallucinations in Factual Question Answeringcited by 54
  10. 2024InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answerscited by 26
  11. 2024Mitigating Large Language Model Hallucination with Faithful Finetuningcited by 24
  12. 2023Towards reducing hallucination in extracting information from financial reports using Large Language Modelscited by 11
2 more
  1. 2024HILL: A Hallucination Identifier for Large Language Modelscited by 11
  2. 2024Generation Constraint Scaling Can Mitigate Hallucinationcited by 4

Built on by

Not cited yet.