@inproceedings{gao-etal-2026-uir,
title = "uir-cis-7 at {S}em{E}val-2026 Task 7: Zero-Shot Chain-of-Thought Reasoning for Cross-Cultural Daily Knowledge",
author = "Gao, Jianning and
Mao, Xianling and
Shi, Shumin and
Zhaxi, Duanzhi and
Sun, Yingbo and
Li, Xiandeng and
Li, Binyang",
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-1.399/",
pages = "3182--3187",
ISBN = "979-8-89176-414-9",
abstract = "SemEval-2026 Task 7 evaluates the ability of Large Language Models (LLMs) to reason about diverse daily knowledge across 30 geographic regions. In this paper, team uir-cis-7 approaches this challenge not merely as an accuracy optimization problem, but as a diagnostic probe to evaluate the representational limits of LLMs without fine-tuning. To address Western-centric bias and the ``overthinking penalty'' frequently observed in high-resource contexts, we introduce a Two-Tier Dynamic Routing framework. Based on cultural resource density, queries are routed either to a direct-answer pathway or a complex reasoning pathway. The complex pathway utilizes an Anti-Bias Persona-Conditioned Chain-of-Thought enhanced with Knowledge Anchoring and multi-path Self-Consistency voting to mitigate majority-culture heuristics. Evaluated using a strict macro-average metric, our system achieved an overall accuracy of 89.02{\%} on the official leaderboard. Our fine-grained evaluation and theoretical error analysis quantify the epistemological boundaries of prompt-based alignment, proving our dynamic strategy effectively rescues marginalized cultural knowledge while exposing persistent instances where safety-aligned models project Western progressive norms onto traditional contexts. Furthermore, cross-model validation on open-source architectures explicitly confirms our framework{'}s generalizability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2026-uir">
<titleInfo>
<title>uir-cis-7 at SemEval-2026 Task 7: Zero-Shot Chain-of-Thought Reasoning for Cross-Cultural Daily Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianning</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianling</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shumin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duanzhi</namePart>
<namePart type="family">Zhaxi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingbo</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiandeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyang</namePart>
<namePart type="family">Li</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>SemEval-2026 Task 7 evaluates the ability of Large Language Models (LLMs) to reason about diverse daily knowledge across 30 geographic regions. In this paper, team uir-cis-7 approaches this challenge not merely as an accuracy optimization problem, but as a diagnostic probe to evaluate the representational limits of LLMs without fine-tuning. To address Western-centric bias and the “overthinking penalty” frequently observed in high-resource contexts, we introduce a Two-Tier Dynamic Routing framework. Based on cultural resource density, queries are routed either to a direct-answer pathway or a complex reasoning pathway. The complex pathway utilizes an Anti-Bias Persona-Conditioned Chain-of-Thought enhanced with Knowledge Anchoring and multi-path Self-Consistency voting to mitigate majority-culture heuristics. Evaluated using a strict macro-average metric, our system achieved an overall accuracy of 89.02% on the official leaderboard. Our fine-grained evaluation and theoretical error analysis quantify the epistemological boundaries of prompt-based alignment, proving our dynamic strategy effectively rescues marginalized cultural knowledge while exposing persistent instances where safety-aligned models project Western progressive norms onto traditional contexts. Furthermore, cross-model validation on open-source architectures explicitly confirms our framework’s generalizability.</abstract>
<identifier type="citekey">gao-etal-2026-uir</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.399/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3182</start>
<end>3187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T uir-cis-7 at SemEval-2026 Task 7: Zero-Shot Chain-of-Thought Reasoning for Cross-Cultural Daily Knowledge
%A Gao, Jianning
%A Mao, Xianling
%A Shi, Shumin
%A Zhaxi, Duanzhi
%A Sun, Yingbo
%A Li, Xiandeng
%A Li, Binyang
%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 gao-etal-2026-uir
%X SemEval-2026 Task 7 evaluates the ability of Large Language Models (LLMs) to reason about diverse daily knowledge across 30 geographic regions. In this paper, team uir-cis-7 approaches this challenge not merely as an accuracy optimization problem, but as a diagnostic probe to evaluate the representational limits of LLMs without fine-tuning. To address Western-centric bias and the “overthinking penalty” frequently observed in high-resource contexts, we introduce a Two-Tier Dynamic Routing framework. Based on cultural resource density, queries are routed either to a direct-answer pathway or a complex reasoning pathway. The complex pathway utilizes an Anti-Bias Persona-Conditioned Chain-of-Thought enhanced with Knowledge Anchoring and multi-path Self-Consistency voting to mitigate majority-culture heuristics. Evaluated using a strict macro-average metric, our system achieved an overall accuracy of 89.02% on the official leaderboard. Our fine-grained evaluation and theoretical error analysis quantify the epistemological boundaries of prompt-based alignment, proving our dynamic strategy effectively rescues marginalized cultural knowledge while exposing persistent instances where safety-aligned models project Western progressive norms onto traditional contexts. Furthermore, cross-model validation on open-source architectures explicitly confirms our framework’s generalizability.
%U https://aclanthology.org/2026.semeval-1.399/
%P 3182-3187
Markdown (Informal)
[uir-cis-7 at SemEval-2026 Task 7: Zero-Shot Chain-of-Thought Reasoning for Cross-Cultural Daily Knowledge](https://aclanthology.org/2026.semeval-1.399/) (Gao et al., SemEval 2026)
ACL
- Jianning Gao, Xianling Mao, Shumin Shi, Duanzhi Zhaxi, Yingbo Sun, Xiandeng Li, and Binyang Li. 2026. uir-cis-7 at SemEval-2026 Task 7: Zero-Shot Chain-of-Thought Reasoning for Cross-Cultural Daily Knowledge. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 3182–3187, San Diego, California, USA. Association for Computational Linguistics.