The Geometry of Language: Understanding LLMs in Bioethics.

Abstract

In this article, I explored the application of large language models (LLMs) in analysing linguistic colexification and ambiguity within bioethical scenarios. By employing word embeddings derived from LLMs, I constructed semantic distance matrices that provide insight into the relationships between key terms in bioethical vignettes. These matrices were used to quantify and visualize the degree of linguistic ambiguity and specificity across different versions of each vignette-those with high colexification (ambiguous language) and those with low colexification (specific language). The approach taken involves encoding words according to their semantic adjacency and representing these relationships geometrically through distance matrices. The resulting matrices reflect the nuanced differences in how concepts are related within bioethical contexts, offering a quantitative method for analysing language use. The study demonstrates that LLMs, by facilitating geometric representations of language, can enhance our understanding of complex ethical dilemmas by systematically addressing linguistic ambiguity. Ultimately, this research contributes to the field of bioethics by providing a computational approach to improving clarity in ethical communication, highlighting the potential of LLMs to inform both ethical decision-making and discourse analysis. LLMs, while not capable of performing speech acts in the full philosophical sense-as human beings do-still serve as powerful tools to analyse and understand bioethical language. This distinction-between performing speech acts and analysing their linguistic features-highlights the unique contribution of LLMs as analytical tools rather than ethical agents.