Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings.

Word-level psycholinguistic norms are necessary to test theories of language processing. However, obtaining such human-based measures is not always feasible or straightforward. One promising approach is to augment human norming datasets by using large language models (LLMs) to predict these characteristics directly, a practice that is rapidly gaining popularity in psycholinguistics and cognitive science. However, the novelty of this approach (and the relative inscrutability of LLMs) necessitates the adoption of rigorous methodologies. We discuss the range of possible approaches, and clarify limitations that are not immediately apparent. In this work, we present a comprehensive methodology for estimating word characteristics with LLMs, enriched with practical advice and lessons learned from our own experience. Our approach covers both the direct use of base LLMs and the fine-tuning of models, an alternative that can yield substantial performance gains in certain scenarios. A major emphasis in the guide is the need to validate LLM-generated data, at least with a small set of a few hundred human "gold standard" norms, before using the LLM-generated norms. We also present a software framework that implements our methodology and supports both commercial and open-weight models. We illustrate the proposed approach with a case study on estimating word familiarity in English. Using base models, we achieved a Spearman correlation of 0.8 with human ratings, which increased to 0.9 when employing fine-tuned models. This methodology, framework, and set of best practices can serve as a reference for future research on leveraging LLMs for psycholinguistic and lexical studies.