@inproceedings{chowdhury-etal-2026-cuetclashing,
    title = "{CUETC}lashing at {S}em{E}val-2026 Task 1: Multilingual Joke Generation Under Lexical and Topical Constraints Using Small Instruction-Tuned {LLM}s",
    author = "Chowdhury, Madiha Ahmed  and
      Khan, Lamia  and
      Fariha, Faozia  and
      Shohan, Symom Hossain  and
      Hoque, Mohammed Moshiul",
    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-1.359/",
    pages = "2860--2865",
    ISBN = "979-8-89176-414-9",
    abstract = "Generating humorous text is one of the most challenging tasks in natural language generation, as models must simultaneously juggle creativity, cultural understanding, and rules. To tackle these issues, this paper introduces our system for Subtask A of SemEval-2026 Task 1: MWAHAHA - Models Write Automatic Humor And Humans Annotate, which asks for single-sentence jokes with two rules{---}certain words must be included, and the joke must relate to a news headline{---}in English, Spanish, and Chinese. Our method uses instruction-tuned language models: Qwen2.5-3B-Instruct for English and Chinese, and Salamandra-2B-Instruct for Spanish, paired with language-specific prompts, special sampling for outputs, and a strong cleaning process after jokes are generated. Without additional task-specific training, our system generates jokes that adhere to the rules in all three languages, demonstrating that simple prompt design and small, instruction-tuned models can be a strong, efficient way to generate funny text across multiple languages."
}