Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models

Zichao Lin, Shuyan Guan, Wending Zhang, Huiyan Zhang, Yugang Li, Huaping Zhang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Recently, large language models (LLMs) have attracted considerable attention due to their remarkable capabilities. However, LLMs’ generation of biased or hallucinatory content raised significant concerns, posing major challenges for their practical application. Many studies have dedicated efforts to address these critical issues, adopting various approaches to mitigate bias and hallucinations in LLM-generated content. Remarkably, no review papers have synthesized insights on these two primary problems. Addressing this gap, this paper aims to conduct a simultaneous and dual-focused review of the current landscape of research. The discussions encompass widely used and newly proposed benchmarks and evaluation methods on bias and hallucination in LLMs. This paper also investigates advanced mitigation methods and present a taxonomy based on different mitigation strategies. Moreover, a comparative analysis of the sources, mitigation methods, and evaluation methods for bias and hallucination is included. In the end, this paper provides a synthesis of current research trends and suggests potential directions for future research to address bias and hallucination in LLMs, considering the ongoing challenges in this field.

Original languageEnglish
Article number243
JournalArtificial Intelligence Review
Volume57
Issue number9
DOIs
Publication statusPublished - Sept 2024

Keywords

  • Debias
  • Hallucination
  • Large language models
  • Survey

Fingerprint

Dive into the research topics of 'Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models'. Together they form a unique fingerprint.

Cite this