Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts

Metehan Oğuz, Yusuf Ciftci, Yavuz Faruk Bakman


Abstract
Large language models (LLMs) have shown impressive capabilities in tasks such as machine translation, text summarization, question answering, and solving complex mathematical problems. However, their primary training on data-rich languages like English limits their performance in low-resource languages. This study addresses this gap by focusing on the Indexical Shift problem in Turkish. The Indexical Shift problem involves resolving pronouns in indexical shift contexts, a grammatical challenge not present in high-resource languages like English. We present the first study examining indexical shift in any language, releasing a Turkish dataset specifically designed for this purpose. Our Indexical Shift Dataset consists of 156 multiple-choice questions, each annotated with necessary linguistic details, to evaluate LLMs in a few-shot setting. We evaluate recent multilingual LLMs, including GPT-4, GPT-3.5, Cohere-AYA, Trendyol-LLM, and Turkcell-LLM, using this dataset. Our analysis reveals that even advanced models like GPT-4 struggle with the grammatical nuances of indexical shift in Turkish, achieving only moderate performance. These findings underscore the need for focused research on the grammatical challenges posed by low-resource languages. We released the dataset and code here.
Anthology ID:
2024.sigturk-1.5
Volume:
Proceedings of the First Workshop on Natural Language Processing for Turkic Languages (SIGTURK 2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand and Online
Editors:
Duygu Ataman, Mehmet Oguz Derin, Sardana Ivanova, Abdullatif Köksal, Jonne Sälevä, Deniz Zeyrek
Venues:
SIGTURK | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
53–61
Language:
URL:
https://aclanthology.org/2024.sigturk-1.5
DOI:
Bibkey:
Cite (ACL):
Metehan Oğuz, Yusuf Ciftci, and Yavuz Faruk Bakman. 2024. Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts. In Proceedings of the First Workshop on Natural Language Processing for Turkic Languages (SIGTURK 2024), pages 53–61, Bangkok, Thailand and Online. Association for Computational Linguistics.
Cite (Informal):
Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts (Oğuz et al., SIGTURK-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigturk-1.5.pdf