Papers by Ivan Ernesto Perez Mejia
Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work evaluating emotion and affective understanding in large language models rely on predetermined label sets or focus on a singular evaluation task. |
| Approach: | They examine the ability of multilingual language models to predict any term used by an author to label their own feelings or emotions. |
| Outcome: | The proposed models perform poorly on three different tasks in English and Spanish. |