3 papers
cs.CL2026
Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors
Ryota Mibayashi, Hiroaki Ohshima
Large language models (LLMs) have achieved strong performance across various natural language processing tasks. However, their robustness to typographical errors remains underexplo…
cs.MM2026
Supporting Perspective Acquisition and Opinion Formation on Societal Issues Through AI-Generated Japanese Rap Battle Debates
Ryota Mibayashi, Toru Urakawa, Dai Takanashi +9
Acquiring diverse perspectives and forming informed opinions on societal issues are essential for critical thinking and informed decision-making. Although observing debates between…
cs.CL2026
YOMI-Bench: A Benchmark for Evaluating Kanji Reading and Phonological Understanding of LLMs for Japanese
Ryota Mibayashi, Hiroya Takamura, Hitomi Yanaka
We propose YOMI-Bench, a benchmark for evaluating kanji reading and phonological understanding of large language models (LLMs) for Japanese. In Japanese, a single kanji character o…