Why do AI chatbots make things up?

Numbers match the citations in the article. A working link isn't proof that a page supports a claim; check the quoted passage and date.

1. 1

   Large Language Models Hallucination: A Comprehensive Survey

   arXiv (Cornell University) (Alansari & Luqman)Published Oct 5, 2025Checked Oct 10, 2026

   “Hallucination refers to the generation of content by an LLM that is fluent and syntactically correct but factually inaccurate or unsupported by external evidence. Hallucinations undermine the reliability and trustworthiness of LLMs, especially in domains requiring factual accuracy. This survey provides a comprehensive review of research on hallucination in LLMs, with a focus on causes, detection, and mitigation. We first present a taxonomy of hallucination types and analyze their root causes across the entire LLM development lifecycle, from data collection and architecture design to inference. We further examine how hallucinations emerge in key natural language generation tasks. Building on this foundation, we introduce a structured taxonomy of detection approaches and another taxonomy of mitigation strategies. We also analyze the strengths and limitations of current detection and mitigation approaches and review existing evaluation benchmarks and metrics used to quantify LLMs hallucinations. Finally, we outline key open challenges and promising directions for future research, providing a foundation for the development of more truthful and trustworthy LLMs.”

2. 2

   AI Hallucinations in Large Language Model and Multimodal Models: A Systematic Review of Causes, Types, Detection, Mitigation, and Future Directions

   International Journal of Computer Sciences and Engineering (Singh & Banerjee)Published Jun 30, 2026Checked Oct 10, 2026

   “Language models are the problem and language models need to be fixed. This paper explores a problem that earlier research had left unexplored. It does this by reviewing existing studies and combining a mathematical theory with a clear step-, by-step approach. The researchers followed a process to find studies published between 2018 and 2026. They applied rules to screen these studies and narrowed them down to a smaller group. This group was then examined across eight themes. What they found is that AI “hallucinations” (when AI makes up false information) come from several factors working together: the data, the system's design, how it's trained, how it generates answers, and how it's tested. Recent theory suggests hallucination is a built-in feature of how these AI systems generate text, not a flaw that can simply be removed. They identified eight types of hallucinations, and these types vary in how hard they are to detect and correct. Some detection methods have improved, but the techniques used to reduce hallucinations only lessen the problem—they don't get rid of it completely. The most serious real-world harms show up in legal and medical settings.”

3. 3

   Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models

   arXiv (Cornell University) (Zhang et al.)Published Sep 3, 2023Checked Oct 10, 2026

   “While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.”

4. 4

   Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models

   arXiv (Cornell University) (Zhang et al.)Published Jul 10, 2024Checked Oct 10, 2026

   “We coin this phenomenon as ``knowledge overshadowing'': when we query knowledge from a language model with multiple conditions, some conditions overshadow others, leading to hallucinated outputs. This phenomenon partially stems from training data imbalance, which we verify on both pretrained models and fine-tuned models, over a wide range of LM model families and sizes.From a theoretical point of view, knowledge overshadowing can be interpreted as over-generalization of the dominant conditions (patterns). We show that the hallucination rate grows with both the imbalance ratio (between the popular and unpopular condition) and the length of dominant condition description, consistent with our derived generalization bound. Finally, we propose to utilize overshadowing conditions as a signal to catch hallucination before it is produced, along with a training-free self-contrastive decoding method to alleviate hallucination during inference. Our proposed approach showcases up to 82% F1 for hallucination anticipation and 11.2% to 39.4% hallucination control, with different models and datasets.”

5. 5

   A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

   ACM Transactions on Information Systems (Huang et al.)Published Nov 20, 2024Checked Oct 10, 2026

   “Given the open-ended general-purpose attributes inherent to LLMs, LLM hallucinations present distinct challenges that diverge from prior task-specific models. This divergence highlights the urgency for a nuanced understanding and comprehensive overview of recent advances in LLM hallucinations. In this survey, we begin with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, we present a thorough overview of hallucination detection methods and benchmarks. Our discussion then transfers to representative methodologies for mitigating LLM hallucinations. Additionally, we delve into the current limitations faced by retrieval-augmented LLMs in combating hallucinations, offering insights for developing more robust IR systems. Finally, we highlight the promising research directions on LLM hallucinations, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.”

6. 6

   Survey of Hallucination in Natural Language Generation

   ACM Computing Surveys (Ji et al.)Published Nov 17, 2022Checked Oct 10, 2026

   “This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.”