A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models

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

Closest papers

1. Very close Not relevant

   Hallucination Mitigation Techniques in Large Language Models

   M. Abdelghafour, Mohammed Mabrouk, Zaki Taha · 2024 · International Journal of Intelligent Computing and Information Sciences · cited 22 times · Not summarized yet

   Abstract

   : Large language models (LLMs) have demonstrated impressive natural language understanding and generation capabilities, enabling advancements in diverse fields such as customer support, healthcare, and content creation. However, a significant challenge with LLMs is their tendency to produce factually inaccurate or nonsensical information, commonly known as hallucination. Hallucinations not only compromise the reliability of these models but can also lead to serious ethical and practical issues, particularly in high-stakes applications. This survey comprehensively reviews recent advancements in hallucination mitigation strategies for LLMs. We explore retrieval-augmented models, which enhance …

2. Very close Cites this paper Not relevant

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

   Lei Huang, Weijiang Yu, Weitao Ma et al. · 2023 · Computation and Language · cited 2,539 times · AI summary available

   Abstract

   The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), leading to remarkable advancements in text understanding and generation. Nevertheless, alongside these strides, LLMs exhibit a critical tendency to produce hallucinations, resulting in content that is inconsistent with real-world facts or user inputs. This phenomenon poses substantial challenges to their practical deployment and raises concerns over the reliability of LLMs in real-world scenarios, which attracts increasing attention to detect and mitigate these hallucinations. In this survey, we aim to provide a thorough and in-depth overview of recent advances in the fie…

3. Very close Not relevant

   From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs

   Ioannis Kazlaris, E. Antoniou, Konstantinos I. Diamantaras et al. · 2025 · Applied Informatics · cited 13 times · Not summarized yet

   Abstract

   Large Language Models (LLMs) exhibit remarkable generative capabilities but remain vulnerable to hallucinations—outputs that are fluent yet inaccurate, ungrounded, or inconsistent with source material. To address the lack of methodologically grounded surveys, this paper introduces a novel method-oriented taxonomy of hallucination mitigation strategies in text-based LLMs. The taxonomy organizes over 300 studies into six principled categories: Training and Learning Approaches, Architectural Modifications, Input/Prompt Optimization, Post-Generation Quality Control, Interpretability and Diagnostic Methods, and Agent-Based Orchestration. Beyond mapping the field, we identify persistent challenges…

4. Very close Not relevant

   Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review

   S. Kumar · 2025 · Journal of Information Systems Engineering & Management · cited 5 times · Not summarized yet

   Abstract

   Large Language Models have achieved unprecedented capabilities in natural language generation but remain vulnerable to hallucinations—outputs that are fluent and plausible yet factually incorrect or ungrounded. This comprehensive review examines the current landscape of hallucination detection and mitigation in LLMs, analyzing the theoretical foundations, detection methodologies, and mitigation strategies that have emerged to address this critical challenge. To explore the fundamental taxonomy distinguishing intrinsic hallucinations that deviate from input content from extrinsic hallucinations that contradict real-world facts, while examining how these manifestations vary across different na…

5. Very close Not relevant

   Hallucination in Large Language Models: A Comprehensive Survey, Taxonomy, and Mitigation Strategies

   Sudhakar Murthy Molli, Ramya Krishna Kurra · 2026 · International Journal of Engineering Technology and Management Sciences · cited 1 time · Not summarized yet

   Abstract

   Large Language Models (LLMs) have demonstrated impressive performance in a wide range of natural language processing operations, but their propensity to produce plausible-sounding, but factually incorrect information is often known as hallucination is a significant impediment to their use in high-stakes areas of application, like medicine, law, and scientific research. It is in this paper that the current state-of-the-art LLMs have their hallucination phenomena surveyed, and a new four-tier taxonomy defining hallucinations by origin is introduced: (1) intrinsic factual contradictions, (2) extrinsic knowledge conflicts, (3) temporal reasoning failures, and (4) contextual coherence breakdowns.…

6. Very close Cites this paper Not relevant

   Large Language Models Hallucination: A Comprehensive Survey

   Aisha Alansari, Hamzah Luqman · 2025 · Computer Science Review · cited 127 times · Not summarized yet

   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…

7. Very close Cites this paper Not relevant

   Evaluating Hallucinations in Large Language Models(LLM):Metrics and Mitigation

   Thrilok. Koll, T. Babu, Rekha R. Nair · 2025 · 2025 IEEE 6th India Council International Subsections Conference (INDISCON) · Not summarized yet

   Abstract

   Large Language Models’ (LLMs’) quick development has transformed natural language processing and made it possible to produce content that appears human in a variety of applications. One major issue that still exists, though, is the problem of hallucinations, in which LLMs generate information that is not supported by the incoming data or empirical knowledge. These hallucinations pose hazards in crucial applications, including the legal, medical, and educational fields, by compromising the quality and dependability of AIgenerated content. Resolving this issue is essential for enhancing the reliability and practical applications of LLMs. Through a thorough approach that incorporates quantitati…

8. Very close Not relevant

   Understanding and Mitigating Hallucinations in Large Language Models: Insights from a Systematic Literature Review

   Ravneet Singh, Parminder Singh, Arun Malik et al. · 2025 · 2025 International Conference on Metaverse and Current Trends in Computing (ICMCTC) · cited 1 time · Not summarized yet

   Abstract

   The analysis of hallucinations in Large Language Models (LLMs), sequences that are coherent but factually false and semantically conflicting, has implications for the credibility and practical value of such systems. To address this concerning issue, the current paper presents a three-tier systematic review of 30 foundational and state-of-the-art publications, summarizing the existing knowledge on the error’s nature of hallucinations in LLMs and their antecedents and management. The classification of hallucinations is analyzed as intrinsic, extrinsic, compounding, and multimodal errors; focusing on their phenomenon in tasks of questions answering, summarization, and other multimodal cases. Cu…

Prior work it builds on

1. Very close Not relevant

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

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

   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 …

2. Very close A method it uses Not relevant

   A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation

   Neeraj Varshney, Wenlin Yao, Hong-Ming Zhang et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 285 times · Not summarized yet

   Abstract

   Recently developed large language models have achieved remarkable success in generating fluent and coherent text. However, these models often tend to 'hallucinate' which critically hampers their reliability. In this work, we address this crucial problem and propose an approach that actively detects and mitigates hallucinations during the generation process. Specifically, we first identify the candidates of potential hallucination leveraging the model's logit output values, check their correctness through a validation procedure, mitigate the detected hallucinations, and then continue with the generation process. Through extensive experiments with GPT-3.5 (text-davinci-003) on the 'article gen…

3. Very close A method it uses Not relevant

   Teaching Language Models to Hallucinate Less with Synthetic Tasks

   Erik Jones, Hamid Palangi, Clarisse Simoes et al. · 2023 · International Conference on Learning Representations · cited 49 times · Not summarized yet

   Abstract

   Large language models (LLMs) frequently hallucinate on abstractive summarization tasks such as document-based question-answering, meeting summarization, and clinical report generation, even though all necessary information is included in context. However, optimizing LLMs to hallucinate less on these tasks is challenging, as hallucination is hard to efficiently evaluate at each optimization step. In this work, we show that reducing hallucination on a synthetic task can also reduce hallucination on real-world downstream tasks. Our method, SynTra, first designs a synthetic task where hallucinations are easy to elicit and measure. It next optimizes the LLM's system message via prefix-tuning on t…

4. Very close Not relevant

   Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification

   Haoqiang Kang, Jun-Tong Ni, Huaxiu Yao · 2023 · arXiv.org · preprint, not peer reviewed · cited 62 times · Not summarized yet

   Abstract

   Large Language Models (LLMs) have demonstrated remarkable proficiency in generating fluent text. However, they often encounter the challenge of generating inaccurate or hallucinated content. This issue is common in both non-retrieval-based generation and retrieval-augmented generation approaches, and existing post-hoc rectification methods may not address the accumulated hallucination errors that may be caused by the"snowballing"issue, especially in reasoning tasks. To tackle these challenges, we introduce a novel approach called Real-time Verification and Rectification (Ever). Instead of waiting until the end of the generation process to rectify hallucinations, Ever employs a real-time, ste…

5. Very close Not relevant

   Trapping LLM Hallucinations Using Tagged Context Prompts

   Philip Feldman, James R. Foulds, Shimei Pan · 2023 · Computation and Language · preprint, not peer reviewed · cited 63 times · AI summary available

   Abstract

   Recent advances in large language models (LLMs), such as ChatGPT, have led to highly sophisticated conversation agents. However, these models suffer from "hallucinations," where the model generates false or fabricated information. Addressing this challenge is crucial, particularly with AI-driven platforms being adopted across various sectors. In this paper, we propose a novel method to recognize and flag instances when LLMs perform outside their domain knowledge, and ensuring users receive accurate information. We find that the use of context combined with embedded tags can successfully combat hallucinations within generative language models. To do this, we baseline hallucination frequency i…

Papers that cite it

1. Very close Uses this paper in depth Not relevant

   Hallucinations in Large Language Models for Education: Challenges and Mitigation

   K. U. Danyaro, Shamsu Abdullahi, A. Abdallah et al. · 2025 · International Journal of Teaching, Learning and Education · cited 27 times · Not summarized yet

   Abstract

   Large Language Models (LLMs) are increasingly being adopted in education to support teaching, learning, and assessment. While they offer benefits such as personalised learning and automated feedback, their tendency to generate hallucinations (plausible but factually incorrect or fabricated information) poses a critical challenge. In an educational context, hallucinations risk misleading students, compromising academic integrity, and eroding trust in AI-assisted learning. This paper examines hallucinations in education, highlighting their causes, risks, and implications. Unlike prior surveys that address hallucinations broadly, our work focuses specifically on education, where the consequence…

2. Very close Not relevant

   Mitigating Hallucinations in Large Language Models via Retrieval Augmented Generation: A Systematic Review of n8n-Based Implementations

   I. K. W. Adnyana, Rosalin Theophilia Tayane, Fahmi Fahmi et al. · 2026 · EDUKASIA Jurnal Pendidikan dan Pembelajaran · cited 1 time · Not summarized yet

   Abstract

   This study systematically examines hallucination phenomena in Large Language Models (LLMs), focusing on their characteristics, causal factors, and mitigation strategies through Retrieval-Augmented Generation (RAG) and low-code orchestration platforms such as n8n. Using a Systematic Literature Review (SLR) approach based on PRISMA 2020 guidelines, this study analysed 40 peer-reviewed articles published between 2020 and 2025 from major scientific databases. The findings reveal that hallucinations are multidimensional, consisting of factual, semantic, and contextual hallucinations influenced by static training data, probabilistic token prediction, prompt ambiguity, and insufficient validation m…

3. Very close Not relevant

   Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models

   Matthew Dahl, Varun Magesh, Mirac Süzgün et al. · 2024 · The Journal of Legal Analysis · cited 345 times · Not summarized yet

   Abstract

   Abstract Do large language models (LLMs) know the law? LLMs are increasingly being used to augment legal practice, education, and research, yet their revolutionary potential is threatened by the presence of “hallucinations”—textual output that is not consistent with legal facts. We present the first systematic evidence of these hallucinations in public-facing LLMs, documenting trends across jurisdictions, courts, time periods, and cases. Using OpenAI’s ChatGPT 4 and other public models, we show that LLMs hallucinate at least 58% of the time, struggle to predict their own hallucinations, and often uncritically accept users’ incorrect legal assumptions. We conclude by cautioning against the ra…

4. Very close Not relevant

   Exploring RAG Solutions to Reduce Hallucinations in LLMs

   Samar AboulEla, Paria Zabihitari, Nourhan Ibrahim et al. · 2025 · IEEE International Systems Conference (SysCon) · cited 27 times · Not summarized yet

   Abstract

   Large Language Models (LLMs) often face challenges in generating accurate and reliable information, particularly in knowledge-intensive tasks. This limitation, referred to as hallucination, occurs when models produce content that is incorrect, irrelevant, or unsupported by evidence. Retrieval Augmented Generation (RAG) solutions provide a promising approach by integrating relevant external knowledge, enabling models to generate factually grounded responses. This study evaluates the performance of a base LLM model, a fine-tuned DistilBERT model, and two RAG architectures, Naïve RAG and Graph RAG, to study their impact on reducing hallucinations and enhancing contextual understanding. Using su…

5. Very close Not relevant

   Prompt Engineering Based Factivity Hallucination Alleviation System for Large Language Models

   He-Sen Yang, Na Zeng, Tian-Xiang Cui et al. · 2026 · 2026 International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · cited 1 time · Not summarized yet

   Abstract

   Large Language Models (LLMs) show excellent abilities in various applications. However, they tend to produce hallucinations—-fabricated or factually incorrect information, which reduces their reliability. Therefore, LLMs hallucination has become an increasingly prominent problem, urgently requiring improvements in the factual consistency of model outputs. This paper proposes a prompt engineering framework that can comprehensively alleviate the fact hallucination. The proposed approach combines dynamic threshold mechanisms, cross-validation, self-verification, chain-of-thought reasoning, and retrieval-augmented generation techniques. Extensive experiments were conducted using the Claude 3.7 a…