De Sa J.M.C., Lee J., Pruski C., Da Silveira M.
Eacl 2026 6th International Workshop on Computational Approaches to Language Change Lchange 2026 Proceedings of the Workshop, pp. 110-123, 2026
Languages continually evolve in response to societal events, resulting in new terms and semantic shifts. These changes have significant implications for computer applications, including automatic translation and chatbots, making it essential to characterize them accurately. The recent development of Large Language Models (LLMs) has notably advanced natural language understanding, particularly in sense inference and reasoning. In this paper, we investigate the potential of LLMs in characterizing three aspects of polysemy and semantic shift: dimension, relation, and orientation. We achieve this by combining the reasoning capabilities of LLMs with rhetorical devices and conducting an experimental assessment of our approach using newly created datasets. Our results highlight the effectiveness of LLMs in capturing and analyzing semantic shifts, providing valuable insights to improve computational linguistic applications.
