@inproceedings{iranmanesh-etal-2026-guir,
    title = "{GUIR} at {S}em{E}val-2026 Task 7: Probing Cultural Knowledge in {LLM}s via Multi-Agent Debate",
    author = "Iranmanesh, Reihaneh  and
      Frieder, Ophir  and
      Goharian, Nazli",
    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-1.438/",
    pages = "3549--3561",
    ISBN = "979-8-89176-414-9",
    abstract = "We present the GUIR system for SemEval-2026 Task 7, Everyday Knowledge Across Diverse Languages and Cultures, which probes the extent to which general-purpose LLMs encode cultural knowledge without any culture-specific supervision or fine-tuning. Our system addresses two tracks built on the BLEnD benchmark. For the short-answer question (SAQ) track, we employ zero-shot prompting with gpt-4.1, achieving 55.5{\%} accuracy across 61 language locales. For the multiple-choice question (MCQ) track, we propose a three-stage pipeline: (1) zero-shot chain-of-thought inference with gpt-5-mini, (2) cross-locale majority voting to correct inconsistent predictions, and (3) a multi-agent debate protocol in which three LLM instances argue and adjudicate over residual errors. This pipeline achieves 97.47{\%} overall accuracy across 30 locales, ranking first among all submitted systems on the MCQ track. We further conduct a targeted human evaluation on the Persian locale, revealing that BLEnD{'}s lemma-matching scorer systematically underestimates model performance, with human annotators scoring the system 18 percentage points higher than the lemma-matching evaluation. This reveals the need for better evaluation of morphologically rich languages like Persian."
}