@inproceedings{eskandari-etal-2026-minds,
    title = "{MINDS} at {S}em{E}val-2026-Task 1: Enhancing Humor Generation through {RAG} and Synthetic {DPO} Alignment",
    author = "Eskandari, Sina  and
      Mousavi, Seyed Amirreza  and
      Rahimi, Amirreza  and
      Pouresmaeil, Mona  and
      Vitaggio, Marcello  and
      Savelli, Claudio  and
      Coppola, Riccardo  and
      Giobergia, Flavio",
    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-1.372/",
    pages = "2967--2971",
    ISBN = "979-8-89176-414-9",
    abstract = "Humor generation presents significant challenges due to subjectivity and the limitations of automatic metrics. In this work, we address Task 1 of SemEval 2026 (Subtask A) by evaluating three instruction-tuned models (Llama 3.1, Gemma 2, and Qwen 2.5) via a round-robin LLM judging framework. We investigate the impact of Retrieval-Augmented Generation and Direct Preference Optimization (DPO) on performance. Our results identify Llama 3.1 as the strongest baseline and demonstrate that DPO consistently improves humor quality across configurations. These findings confirm the efficacy of LLM-based judging as a practical training signal for optimizing subjective generation tasks."
}