Hallucinations in LLMs and Resolving Them: A Holistic Approach

Rajarshi Biswas, Sourav Dutta, Dirk Werth

2025

Abstract

Generative artificial intelligence, in recent times, is producing tremendous interest across industry and academia leading to rapid growth. Developments in model architecture, training datasets and large scale computing enable the realization of impressive generative tasks in textual computing, computer vision etc. However, the generative processes suffer from various challenging artifacts that can generate confusion, risks or compromise the security. In this paper, we explore in detail the problem of inconsistent or hallucinogenic generation in natural language generation (NLG). We define the problem and survey the current techniques for detection, measurement and mitigation on five different tasks, which are, abstractive summarization, question answering, dialogue generation, machine translation and named entity recognition combined with information retrieval.

Paper Citation

in Harvard Style

Biswas R., Dutta S. and Werth D. (2025). Hallucinations in LLMs and Resolving Them: A Holistic Approach. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 104-115. DOI: 10.5220/0013094500003890

in Bibtex Style

@conference{icaart25,
author={Rajarshi Biswas and Sourav Dutta and Dirk Werth},
title={Hallucinations in LLMs and Resolving Them: A Holistic Approach},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={104-115},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013094500003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Hallucinations in LLMs and Resolving Them: A Holistic Approach
SN - 978-989-758-737-5
AU - Biswas R.
AU - Dutta S.
AU - Werth D.
PY - 2025
SP - 104
EP - 115
DO - 10.5220/0013094500003890
PB - SciTePress