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

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Review Not relevant

   A Survey of Hallucination Problems Based on Large Language Models

   Xinxin Liu · 2024 · Applied and Computational Engineering · cited 33 times · Not summarized yet

   A Survey of Hallucination Problems Based on Large Language Models reviews hallucination types, causes, and solutions in LLMs, overlapping this survey’s broad coverage.

   Abstract

   Abstract. Large language models (LLM) have made significant achievements in the field of natural language processing, but the generated text often contains content that is inconsistent with the real world or user input, known as hallucinations. This article investigates the current situation of hallucinations in LLM, including the definition, types, causes, and solutions of hallucinations. Illusions are divided into different types such as factual and faithful, mainly caused by factors such as training data defects, low utilization of facts, and randomness in the decoding process. The phenomenon of hallucinations poses a threat to the reliability of LLM, especially in fields such as healthca…

2. Very close Review Not relevant

   A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models

   S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Vinija Jain et al. · 2024 · Computation and Language · preprint, not peer reviewed · cited 559 times · AI summary available

   A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models surveys methods for mitigating LLM hallucinations, a focus within this paper’s broader review.

   Abstract

   As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded. This issue of hallucination is arguably the biggest hindrance to safely deploying these powerful LLMs into real-world production systems that impact people's lives. The journey toward widespread adoption of LLMs in practical settings heavily relies on addressing and mitigating hallucinations. Unlike traditional AI systems focused on limited tasks, LLMs have been exposed to vast amounts of online text data during training. While this allows them to display impressive language fluen…

3. Very close Review Not relevant

   Large Language Models Hallucination: A Comprehensive Survey

   Aisha Alansari, Hamzah Luqman · 2025 · Computer Science Review · cited 126 times · Not summarized yet

   Large Language Models Hallucination: A Comprehensive Survey reviews causes, detection, and mitigation of LLM hallucinations, matching this paper’s survey scope.

   Abstract

   Large language models (LLMs) have transformed natural language processing, achieving remarkable performance across diverse tasks. However, their impressive fluency often comes at the cost of producing false or fabricated information, a phenomenon known as hallucination. 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 pres…

4. Very close Broader context Not relevant

   The Troubling Emergence of Hallucination in Large Language Models - An Extensive Definition, Quantification, and Prescriptive Remediations

   Vipula Rawte, Swagata Chakraborty, Agnibh Pathak et al. · 2023 · Conference on Empirical Methods in Natural Language Processing · cited 272 times · Not summarized yet

   The Troubling Emergence of Hallucination in Large Language Models develops fine-grained hallucination categories and mitigation strategies, addressing topics covered by this broader survey.

   Abstract

   The recent advancements in Large Language Models (LLMs) have garnered widespread acclaim for their remarkable emerging capabilities. However, the issue of hallucination has parallelly emerged as a by-product, posing significant concerns. While some recent endeavors have been made to identify and mitigate different types of hallucination, there has been a limited emphasis on the nuanced categorization of hallucination and associated mitigation methods. To address this gap, we offer a fine-grained discourse on profiling hallucination based on its degree, orientation, and category, along with offering strategies for alleviation. As such, we define two overarching orientations of hallucination: …

5. Very close Review Not relevant

   Research Progress on the Hallucination Problem of Large Language Models and Some Mitigation Strategies

   Qifu Luo · 2026 · Applied and Computational Engineering · Not summarized yet

   Research Progress on the Hallucination Problem of Large Language Models and Some Mitigation Strategies reviews hallucination causes and mitigation methods, overlapping this survey’s coverage.

   Abstract

   Although Large Language Models (LLMs) have made significant progress in the field of natural language processing, the hallucination phenomenon has become a core issue in judging their credibility and practicality, which may cause serious consequences, especially in high-risk fields such as medicine and law. This article systematically explains the causes and current situation of LLM hallucinations and focuses on sorting out the current mainstream methods of research on alleviating hallucinations. First, the definition and classification of hallucinations are provided, and then the generation mechanism of hallucinations is explained from various aspects, such as data deviation and training go…

6. Very close Review Not relevant

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

   Yue Zhang, Yafu Li, Leyang Cui et al. · 2023 · Computation and Language · cited 1,233 times · AI summary available

   Siren's Song in the AI Ocean surveys LLM hallucination taxonomies, benchmarks, detection, explanation, and mitigation, closely matching this paper’s scope.

   Abstract

   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, ana…

7. Very close Another approach to the problem Not relevant

   LLM-Check: Investigating Detection of Hallucinations in Large Language Models

   Gaurang Sriramanan, S. Bharti, Vinu Sankar Sadasivan et al. · 2024 · Neural Information Processing Systems · cited 182 times · Not summarized yet

   LLM-Check investigates practical techniques for detecting hallucinations in LLM outputs, whereas this paper surveys detection alongside causes, benchmarks, and mitigation.

   Abstract

   While Large Language Models (LLMs) have become immensely popular due to their outstanding performance on a broad range of tasks, these models are prone to producing hallucinations— outputs that are fallacious or fabricated yet often appear plausible or tenable at a glance. In this paper, we conduct a comprehensive investigation into the nature of hallucinations within LLMs and furthermore explore effective techniques for detecting such inaccuracies in various real-world settings. Prior approaches to detect hallucinations in LLM outputs, such as consistency checks or retrieval-based methods, typically assume access to multiple model responses or large databases. These techniques, however, ten…

8. Very close Another approach to the problem Not relevant

   Detection of Hallucinations Based on the Internal States of Large Language Models

   Timur Rustemovich Aisin, Tatiana Vyacheslavovna Shamardina · 2025 · Russian Digital Libraries Journal · cited 1 time · Not summarized yet

   Detection of Hallucinations Based on the Internal States of Large Language Models investigates detection using LLM internal states, one specialized approach within this survey’s broader topic.

   Abstract

   In recent years, large language models (LLMs) have achieved substantial progress in natural language processing tasks and have become key instruments for addressing a wide range of applied and research problems. However, as their scale and capabilities grow, the issue of hallucinations — i.e., the generation of false, unreliable, or nonexistent information presented in a credible manner—has become increasingly acute. Consequently, analyzing the nature of hallucinations and developing methods for their detection has acquired both scientific and practical significance. This study examines the phenomenon of hallucinations in large language models, reviews their existing classification, and inve…

Prior work it builds on

1. Very close Groundwork for this paper Used in depth by this paper Not relevant

   Survey of Hallucination in Natural Language Generation

   Ziwei Ji, Nayeon Lee, Rita Frieske et al. · 2022 · Computation and Language · cited 6,581 times · AI summary available

   Survey of Hallucination in Natural Language Generation reviews hallucinations in text generation and their evaluation and mitigation, providing earlier background cited by this survey.

   Abstract

   Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent natural language generation, naturally leading to development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also investigated that such generation includes hallucinated texts, which makes the performances of text generation fail to meet users' expectations in many real-world scenarios. In order to address this issue, studies in evaluation and mitigation methods of hallucinations have been presen…

2. Very close Another approach to the problem Not relevant

   Towards Mitigating Hallucination in Large Language Models via Self-Reflection

   Ziwei Ji, Tiezheng Yu, Yan Xu et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 126 times · Not summarized yet

   Towards Mitigating Hallucination in Large Language Models via Self-Reflection analyzes medical generative QA and self-reflection mitigation, a specific application cited by this survey.

   Abstract

   Large language models (LLMs) have shown promise for generative and knowledge-intensive tasks including question-answering (QA) tasks. However, the practical deployment still faces challenges, notably the issue of"hallucination", where models generate plausible-sounding but unfaithful or nonsensical information. This issue becomes particularly critical in the medical domain due to the uncommon professional concepts and potential social risks involved. This paper analyses the phenomenon of hallucination in medical generative QA systems using widely adopted LLMs and datasets. Our investigation centers on the identification and comprehension of common problematic answers, with a specific emphasi…

3. Very close Another approach to the problem Not relevant

   Sources of Hallucination by Large Language Models on Inference Tasks

   Nick McKenna, Tianyi Li, Liang Cheng et al. · 2023 · Conference on Empirical Methods in Natural Language Processing · cited 297 times · Not summarized yet

   Sources of Hallucination by Large Language Models on Inference Tasks uses controlled behavioral studies to identify pretraining biases behind hallucinations, cited as evidence in this survey.

   Abstract

   Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization. We present a series of behavioral studies on several LLM families (LLaMA, GPT-3.5, and PaLM) which probe their behavior using controlled experiments. We establish two biases originating from pretraining which predict much of their behavior, and show that these are major sources of hallucination in generative LLMs. First, memorization at the level of sentences: we show that, regardless of the premise, models falsely label NLI test samples as entailing when the hypothesis is attested in training data, and that entities are used as ``…

4. Very close Another approach to the problem Not relevant

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

   Deren Lei, Yaxi Li, Mengya Hu et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 67 times · Not summarized yet

   Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations proposes CoNLI detection and post-editing, a specific mitigation approach cited by this survey.

   Abstract

   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 …

5. Very close Shared data, tool or method Not relevant

   Chainpoll: A high efficacy method for LLM hallucination detection

   R. Friel, Atindriyo Sanyal · 2023 · arXiv.org · preprint, not peer reviewed · cited 69 times · Not summarized yet

   Chainpoll introduces a hallucination-detection method and RealHall benchmark datasets, contributing a method and evaluation resource cited by this survey.

   Abstract

   Large language models (LLMs) have experienced notable advancements in generating coherent and contextually relevant responses. However, hallucinations - incorrect or unfounded claims - are still prevalent, prompting the creation of automated metrics to detect these in LLM outputs. Our contributions include: introducing ChainPoll, an innovative hallucination detection method that excels compared to its counterparts, and unveiling RealHall, a refined collection of benchmark datasets to assess hallucination detection metrics from recent studies. While creating RealHall, we assessed tasks and datasets from previous hallucination detection studies and observed that many are not suitable for the p…

Papers that cite it

1. Very close Broader context Not relevant

   Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective

   Ernests Lavrinovics, Russa Biswas, Johannes Bjerva et al. · 2024 · Journal of Web Semantics · cited 99 times · Not summarized yet

   Knowledge Graphs, Large Language Models, and Hallucinations examines knowledge graphs as context for reducing LLM hallucinations and cites this survey.

   Abstract

   Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) based applications including automated text generation, question answering, chatbots, and others. However, they face a significant challenge: hallucinations, where models produce plausible-sounding but factually incorrect responses. This undermines trust and limits the applicability of LLMs in different domains. Knowledge Graphs (KGs), on the other hand, provide a structured collection of interconnected facts represented as entities (nodes) and their relationships (edges). In recent research, KGs have been leveraged to provide context that can fill gaps in an LLM’s understanding of certain topics offering a pr…

2. Very close Broader context Uses this paper in depth Not relevant

   What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty

   Hazel H. Kim, Jakub Binkowski, Ekaterina Fadeeva et al. · 2026 · Not summarized yet

   What Hallucinations Have We Measured? argues for a strict definition distinguishing confident errors from uncertainty, challenging terminology used in this survey.

   Abstract

   Hallucination remains one of the most critical challenges in deploying large language models (LLMs) reliably and safely. Yet the term is used inconsistently across the research community. We argue for a strict definition of hallucinations in LLMs. First, hallucinations should be confident incorrectness, kept separate from expressed uncertainty (UNK)1. UNK reveals that the model may be wrong, whereas a hallucination does not reveal it and is therefore more dangerous in practice. Conflating the two obscures their distinct behaviors and makes them hard to study. Second, hallucinations should be split by a simple re-elicitation test: does any semantically equivalent prompt recover the correct re…

3. Very close Review Not relevant

   Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review

   Wan Zhang, Jing Zhang · 2025 · Mathematics · cited 177 times · Not summarized yet

   Hallucination Mitigation for Retrieval-Augmented Large Language Models reviews causes and mitigation in RAG systems, a narrower topic that cites this survey.

   Abstract

   Retrieval-augmented generation (RAG) leverages the strengths of information retrieval and generative models to enhance the handling of real-time and domain-specific knowledge. Despite its advantages, limitations within RAG components may cause hallucinations, or more precisely termed confabulations in generated outputs, driving extensive research to address these limitations and mitigate hallucinations. This review focuses on hallucination in retrieval-augmented large language models (LLMs). We first examine the causes of hallucinations from different sub-tasks in the retrieval and generation phases. Then, we provide a comprehensive overview of corresponding hallucination mitigation techniqu…

4. Very close Broader context Not relevant

   Survey of Different Large Language Model Architectures: Trends, Benchmarks, and Challenges

   Minghao Shao, Abdul Basit, Ramesh Karri et al. · 2024 · IEEE Access · cited 97 times · Not summarized yet

   Survey of Different Large Language Model Architectures reviews LLM architectures, benchmarks, and challenges, providing broader model context and citing this survey.

   Abstract

   Large Language Models (LLMs) represent a class of deep learning models adept at understanding natural language and generating coherent responses to various prompts or queries. These models far exceed the complexity of conventional neural networks, often encompassing dozens of neural network layers and containing billions to trillions of parameters. They are typically trained on vast datasets, utilizing architectures based on transformer blocks. Present-day LLMs are multi-functional, capable of performing a range of tasks from text generation and language translation to question answering, as well as code generation and analysis. An advanced subset of these models, known as Multimodal Large L…

5. Very close Same question Not relevant

   Multi-model assurance analysis showing large language models are highly vulnerable to adversarial hallucination attacks during clinical decision support

   Mahmud Omar, Vera Sorin, Jeremy D. Collins et al. · 2025 · Communications Medicine · cited 204 times · Not summarized yet

   Multi-model assurance analysis tests how fabricated clinical prompt details elicit hallucinations and whether mitigation prompts or temperature changes reduce them.

   Abstract

   Large language models (LLMs) show promise in clinical contexts but can generate false facts (often referred to as “hallucinations”). One subset of these errors arises from adversarial attacks, in which fabricated details embedded in prompts lead the model to produce or elaborate on the false information. We embedded fabricated content in clinical prompts to elicit adversarial hallucination attacks in multiple large language models. We quantified how often they elaborated on false details and tested whether a specialized mitigation prompt or altered temperature settings reduced errors. We created 300 physician-validated simulated vignettes, each containing one fabricated detail (a laboratory …