An Evolutionary Large Language Model for Hallucination Mitigation

TL;DR

EvoLLMs introduces an evolutionary computation-based framework that enhances large language models by generating high-quality QA datasets with reduced hallucinations, outperforming traditional methods in accuracy and efficiency.

Contribution

The paper presents EvoLLMs, a novel framework using genetic algorithms to automate QA dataset creation and mitigate hallucinations in LLMs, improving accuracy and reducing manual effort.

Findings

EvoLLMs outperforms human-generated datasets in relevance and coverage.

The framework nearly matches human performance in hallucination mitigation.

EvoLLMs significantly reduces time and resources for dataset curation.

Abstract

The emergence of LLMs, like ChatGPT and Gemini, has marked the modern era of artificial intelligence applications characterized by high-impact applications generating text, images, and videos. However, these models usually ensue with one critical challenge called hallucination: confident presentation of inaccurate or fabricated information. This problem attracts serious concern when these models are applied to specialized domains, including healthcare and law, where the accuracy and preciseness of information are absolute conditions. In this paper, we propose EvoLLMs, an innovative framework inspired by Evolutionary Computation, which automates the generation of high-quality Question-answering (QA) datasets while minimizing hallucinations. EvoLLMs employs genetic algorithms, mimicking evolutionary processes like selection, variation, and mutation, to guide LLMs in generating accurate, contextually relevant question-answer pairs. Comparative analysis shows that EvoLLMs consistently outperforms human-generated datasets in key metrics such as Depth, Relevance, and Coverage, while nearly matching human performance in mitigating hallucinations. These results highlight EvoLLMs as a robust and efficient solution for QA dataset generation, significantly reducing the time and resources required for manual curation.