Modeling the human lexicon under temperature variations: linguistic factors, diversity and typicality in LLM word associations

TL;DR

This study compares human and large language model word associations to understand how models replicate human lexical patterns, focusing on factors like frequency, concreteness, variability, and typicality across different model sizes and temperature settings.

Contribution

It provides a detailed analysis of how LLMs mimic human lexical behavior, highlighting the effects of model size and temperature on response variability and typicality.

Findings

Larger models produce more typical responses with less variability.

Temperature increases response variability but decreases typicality.

Models replicate human trends for frequency and concreteness.

Abstract

Large language models (LLMs) achieve impressive results in terms of fluency in text generation, yet the nature of their linguistic knowledge - in particular the human-likeness of their internal lexicon - remains uncertain. This study compares human and LLM-generated word associations to evaluate how accurately models capture human lexical patterns. Using English cue-response pairs from the SWOW dataset and newly generated associations from three LLMs (Mistral-7B, Llama-3.1-8B, and Qwen-2.5-32B) across multiple temperature settings, we examine (i) the influence of lexical factors such as word frequency and concreteness on cue-response pairs, and (ii) the variability and typicality of LLM responses compared to human responses. Results show that all models mirror human trends for frequency and concreteness but differ in response variability and typicality. Larger models such as Qwen tend to emulate a single "prototypical" human participant, generating highly typical but minimally variable responses, while smaller models such as Mistral and Llama produce more variable yet less typical responses. Temperature settings further influence this trade-off, with higher values increasing variability but decreasing typicality. These findings highlight both the similarities and differences between human and LLM lexicons, emphasizing the need to account for model size and temperature when probing LLM lexical representations.