A Concise Review of Hallucinations in LLMs and their Mitigation
Parth Pulkundwar, Vivek Dhanawade, Rohit Yadav, Minal Sonkar, Medha Asurlekar, Sarita Rathod

TL;DR
This paper provides a concise overview of hallucinations in large language models, exploring their types, origins, and mitigation strategies to improve reliability in natural language processing.
Contribution
It offers a comprehensive summary of hallucination phenomena in LLMs and reviews current methods for their mitigation, serving as a useful resource for researchers.
Findings
Different types of hallucinations identified
Overview of mitigation techniques provided
Highlights the importance of addressing hallucinations
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMental Health via Writing · Machine Learning in Healthcare · Adversarial Robustness in Machine Learning
