@inproceedings{adam-etal-2026-hausanlp,
    title = "{H}ausa{NLP} at {S}em{E}val-2026 Task 7: Prompt-based {H}ausa Cultural Question Answering",
    author = "Adam, Faisal  and
      Aliyu, Lukman  and
      Aji, Sani  and
      Abubakar, Abdulhamid  and
      Shuaibu, Aliyu Rabiu",
    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-1.218/",
    pages = "1701--1706",
    ISBN = "979-8-89176-414-9",
    abstract = "We describe HausaNLP{'}s submission toSemEval-2026 Task 7 Track 1 (short-answercultural question answering). Our system is atraining-free, prompt-based pipeline targetingnative Hausa (ha-NG). Two design decisionsdistinguish it from a generic zero-shot baseline.We use locale-conditional prompting: ha-NGquestions receive a system prompt instructingconcise standard Hausa output with explicitBoko-script characters ({\'a}, {\^a}, {\^I}, {\'{u}}). Second, weuse a two-model fallback pipeline: GPT-4o handles the primary pass, and Gemini 1.5 Flash retries any rows where the primary call returnedan error or empty output, separating modelknowledge failures from API-availability failures. On the official development leaderboard,our best run reached 36.4 accuracy. Error analysis shows that a non-trivial fraction of failures are placeholder strings caused by APIerrors rather than incorrect generations, andthat surface-level mismatches (verbosity, orthographic variation) account for many of the remaining errors. Code, prompts, and processingscripts are released for reproducibility."
}