cs.CL · 2606.22745 Copy arXiv ID · Jun 22, 2026 Save Language-Specific Sentiment Polarity Biases in Encoder and Large Language Model Classification of Product Reviews Authors: Advita Rajiv , Kavitha Kothur , Gautham Reddy
Organizations: John P. Stevens High School, Edison, NJ 08820 · Ford Foundation, New York, NY 10017 · NC State University, Raleigh, NC 27606
Abstract This study investigates sentiment polarity biases, specifically, differences in how accurately AI models classify positive versus negative reviews across languages and model architectures. Large language models show a negative bias in French and are more accurate on negative reviews, while encoder models exhibit positive bias in Japanese, missing negative reviews that use indirect criticism. These language-specific polarity biases have implications in both social and business domains deploying multilingual sentiment analysis systems.
Explore similar work Jun 11, 2026 · Sangho Kim, Heejin Kim, Yoonhee Park +2 Ideology Large Language Model Bias
Jul 16, 2026 · Ej Zhou, Lucas Resck, Zheng Hui +1 Large Language Model Evaluation
Jun 11, 2026 · cs.CL J/K move · Enter open · S save
Sangho Kim, Heejin Kim, Yoonhee Park, Hyunggeun Jeon +1
Graduate School of Data Science, Seoul National University · Dept. of Computer Science and Engineering, Seoul National University
Political bias in large language models (LLMs) is increasingly significant, but difficult to measure reproducibly across political and linguistic contexts. We introduce Polar, a 4,026-instance multiple-choice benchmark that measures political bias through option-level likelihoods rather than prompt-based generation. Polar covers two ideological axes and eight issue categories derived from the Manifesto Project, and evaluates models in parallel across U.S. and South Korean political contexts. Across 38 LLMs, measured bias varies systematically with political context, issue category, model group, and presentation language. All models lean left-progressive on U.S. political content, but show more centered and mixed patterns on South Korean content. Translation experiments further show that presentation language alone can shift measured bias. These findings highlight the need for multilingual and cross-contextual evaluation of political bias in LLMs.