@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iranmanesh-etal-2026-guir">
<titleInfo>
<title>GUIR at SemEval-2026 Task 7: Probing Cultural Knowledge in LLMs via Multi-Agent Debate</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reihaneh</namePart>
<namePart type="family">Iranmanesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ophir</namePart>
<namePart type="family">Frieder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazli</namePart>
<namePart type="family">Goharian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">iranmanesh-etal-2026-guir</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.438/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3549</start>
<end>3561</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GUIR at SemEval-2026 Task 7: Probing Cultural Knowledge in LLMs via Multi-Agent Debate
%A Iranmanesh, Reihaneh
%A Frieder, Ophir
%A Goharian, Nazli
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F iranmanesh-etal-2026-guir
%X 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.
%U https://aclanthology.org/2026.semeval-1.438/
%P 3549-3561
Markdown (Informal)
[GUIR at SemEval-2026 Task 7: Probing Cultural Knowledge in LLMs via Multi-Agent Debate](https://aclanthology.org/2026.semeval-1.438/) (Iranmanesh et al., SemEval 2026)
ACL