Beware of Words: Evaluating the Lexical Diversity of Conversational LLMs using ChatGPT as Case Study

TL;DR

This paper investigates the lexical diversity of conversational LLMs, specifically ChatGPT, highlighting how linguistic features vary with model parameters and emphasizing the importance of evaluating language use in AI-generated texts.

Contribution

It introduces a methodology for assessing lexical richness in LLM outputs and provides a comprehensive analysis of how model parameters influence linguistic diversity.

Findings

Lexical richness varies with ChatGPT versions and parameters

Presence penalty affects diversity of generated text

Role assignment impacts linguistic features

Abstract

The performance of conversational Large Language Models (LLMs) in general, and of ChatGPT in particular, is currently being evaluated on many different tasks, from logical reasoning or maths to answering questions on a myriad of topics. Instead, much less attention is being devoted to the study of the linguistic features of the texts generated by these LLMs. This is surprising since LLMs are models for language, and understanding how they use the language is important. Indeed, conversational LLMs are poised to have a significant impact on the evolution of languages as they may eventually dominate the creation of new text. This means that for example, if conversational LLMs do not use a word it may become less and less frequent and eventually stop being used altogether. Therefore, evaluating the linguistic features of the text they produce and how those depend on the model parameters is the first step toward understanding the potential impact of conversational LLMs on the evolution of languages. In this paper, we consider the evaluation of the lexical richness of the text generated by LLMs and how it depends on the model parameters. A methodology is presented and used to conduct a comprehensive evaluation of lexical richness using ChatGPT as a case study. The results show how lexical richness depends on the version of ChatGPT and some of its parameters, such as the presence penalty, or on the role assigned to the model. The dataset and tools used in our analysis are released under open licenses with the goal of drawing the much-needed attention to the evaluation of the linguistic features of LLM-generated text.