The "LLM World of Words" English free association norms generated by large language models

Free associations have been extensively used in psychology and linguistics for studying how conceptual knowledge is organized. Recently, the potential of applying a similar approach for investigating the knowledge encoded in LLMs has emerged, specifically as a method for investigating LLM biases. However, the absence of large-scale LLM-generated free association norms that are comparable with human-generated norms is an obstacle to this research direction. To address this, we create a new dataset of LLM-generated free association norms modeled after the "Small World of Words"(SWOW) human-generated norms with nearly 12,000 cue words. We prompt three LLMs (Mistral, Llama3, and Haiku) with the same cues as those in SWOW to generate three novel comparable datasets, the "LLM World of Words" (LWOW). From the datasets, we construct network models of semantic memory that represent the conceptual knowledge possessed by humans and LLMs. We validate the datasets by simulating semantic priming within the network models, and we briefly discuss how the datasets can be used for investigating implicit biases in humans and LLMs.