EUVIMEDEUVIMED entdecken
Crossref

Connecting Language and Emotion in Large Language Models for Human-AI Collaboration

Shadab Hafiz Choudhury

Maryland Shared Open Access Repository (USMAI Consortium) · 01.01.2025

DOI: 10.13016/m2afdj-1q3c ↗

Kurz gefasst

Fachartikel in der Zeitschrift Maryland Shared Open Access Repository (USMAI Consortium), erschienen am 01.01.2025. Verfasst von Shadab Hafiz Choudhury.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models demonstrate linguistic abilities on par with humans, generating short texts, stories, instructions, and even code that抯 often indistinguishable from what is created by humans. This allows humans to use large language models (LLMs) collaboratively� as communication aides or writing assistants.However, humans cannot always assume an LLM will behave the same way another person would. This is particularly evident in subjective scenarios such as where emotion is involved. In this work, I explore to what depth do LLMs perceive and understand human emotions, and look at ways of describing an emotion to an LLM for collaborative work. First, I study the problem of classifying emotions and show that LLMs perform well on their own, and can also improve smaller models at the same task. Secondly, I focus on generating emotions, using the problem space of keyword-constrained generation and a human participant-study to see where human expectations and LLM outputs diverge and how we can minimize any such misalignment. Here, I find that using English Words and Lexical expressions Valence-Arousal-Dominance (VAD) scales lead to good alignment and generation quality, while Numeric dimensions of VAD or Emojis fare worse.

Schlagwörter

large language modelsemotional understandingemotion classificationemotion generationhuman-AI collaborationvalence-arousal-dominanceemoji usehuman-AI alignmentwriting support

Zitieren

APA

Choudhury, S. H. (2025). Connecting Language and Emotion in Large Language Models for Human-AI Collaboration. Maryland Shared Open Access Repository (USMAI Consortium). https://doi.org/10.13016/m2afdj-1q3c

Vancouver

Choudhury SH. Connecting Language and Emotion in Large Language Models for Human-AI Collaboration. Maryland Shared Open Access Repository (USMAI Consortium). 2025. doi:10.13016/m2afdj-1q3c

BibTeX
@article{Choudhury2025,
  author = {Choudhury, Shadab Hafiz},
  title = {Connecting Language and Emotion in Large Language Models for Human-AI Collaboration},
  journal = {Maryland Shared Open Access Repository (USMAI Consortium)},
  year = {2025},
  doi = {10.13016/m2afdj-1q3c}
}
Kostenlos starten →