@inproceedings{bazzo-etal-2026-inf,
    title = "{INF}-rsrs at {S}em{E}val-2026 Task 1: Is the best really better? The limits of creative work in the era of {LLM}s",
    author = "Bazzo, Guilherme  and
      Fa{\'e}, Eduardo  and
      Junqueira, J{\'u}lia  and
      Moreira, Higor  and
      Costella Pessutto, Lucas Rafael",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.396/",
    pages = "3156--3164",
    ISBN = "979-8-89176-414-9",
    abstract = "Generating humor is a complex and challenging task for Large Language Models (LLMs), requiring both linguistic creativity and strict adherence to constraints. This paper presents INF-rsrs, our solution for SemEval 2026 Task{\textasciitilde}1: Humor Generation, which tasks models with creating jokes from headlines and word pairs without labeled data. We propose a two-stage framework: a production stage and a selection stage. The production stage employs diverse model families and hyperparameter configurations to generate a wide range of candidate jokes, with each candidate generated by an LLM prompted in the role of a comedian under structured constraints to ensure relevance and humor. Our system was designed to substantiate our claim that the direct use of LLMs in creative works, such as humor generation, hits a hard ceiling that is inescapable through simple prompting. Our proposed system tied in first place in the task ranking, obtaining a top-tier performance."
}