EUVIMEDEUVIMED entdecken
Crossref

Context-Adaptive Humor Rewriting: A First-Order Logic Framework Using Large Language Models

Cheng-En Tsai, Fanfan Chen, Jane Yung-jen Hsu

Proceedings of the AAAI Symposium Series · 18.05.2026 · 8 (1) · 592-596

DOI: 10.1609/aaaiss.v8i1.42592 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 18.05.2026. Verfasst von Cheng-En Tsai und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humor is an important conversational skill that conveys approachability. When addressing different audiences, we often need to adjust and adapt jokes to lower the comprehension barrier while also preventing the original punchline from becoming offensive in a new context. To this end, we propose a humor-rewriting-agent framework. The system converts jokes from an existing humor corpus into a First-Order Logic representation, extracting predicates and constants. The agent then performs context-aware semantic mapping, replacing relevant elements with more suitable equivalents in the target scenario. Finally, the mapped logical structure is realized as fluent, natural text. Through evaluation by participants, this framework provides a controllable, traceable, and interpretable implementation pathway for contextually grounded humor adaptation.

Zitieren

APA

Tsai, C., Chen, F., & Hsu, J. Y. (2026). Context-Adaptive Humor Rewriting: A First-Order Logic Framework Using Large Language Models. Proceedings of the AAAI Symposium Series, 8(1), 592-596. https://doi.org/10.1609/aaaiss.v8i1.42592

Vancouver

Tsai C, Chen F, Hsu JY. Context-Adaptive Humor Rewriting: A First-Order Logic Framework Using Large Language Models. Proceedings of the AAAI Symposium Series. 2026;8(1):592-596. doi:10.1609/aaaiss.v8i1.42592

BibTeX
@article{Tsai2026,
  author = {Tsai, Cheng-En and Chen, Fanfan and Hsu, Jane Yung-jen},
  title = {Context-Adaptive Humor Rewriting: A First-Order Logic Framework Using Large Language Models},
  journal = {Proceedings of the AAAI Symposium Series},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {592--596},
  doi = {10.1609/aaaiss.v8i1.42592}
}
Kostenlos starten →