@inproceedings{abdulmujeeb-aryal-2026-howard,
    title = "{H}oward {U}niversity-{AI}4{PC} at {S}em{E}val-2026 Task 1: Exploring Prompt Strategies for Automatic Humor Generation",
    author = "Abdulmujeeb, Lawal  and
      Aryal, Saurav",
    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-1.319/",
    pages = "2527--2532",
    ISBN = "979-8-89176-414-9",
    abstract = "We present our solution system for SemEval-2026 Task 1-Subtask A, a humor generation task requiring systems to generate jokes, given either a news headline or word-pair inputs. Our approach used the Llama-3.1-8B-Instruct model and we selected this model after comparing several candidate models and humor strategies across our experiments. For the headline inputs, we used a two-shot prompt to frame the output as a tweet and specifying the tone proved to be a particularly important factor in output quality. As for the word-pair inputs, we instructed the model to commit to an everyday situation and generate a funny thought based on that. Also, while experimenting, we noticed that models would start a joke one way with the first word and abruptly shift context mid-joke just to include the second word, and committing to a single situation helped handle that. We also made use of personas here, specifically using Dave Chappelle. Our final system shared 2nd place with 3 other systems out of 32 total systems and achieved an Elo score of 1020. Achieving these results, with no fine-tuning, suggests that careful prompt design alone can yield competitive results."
}