EMNLP 2025 Main

• SPIRIT: Patching Speech Language Models against Jailbreak Attacks. Amirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui, Hanan Aldarmaki, Nils Lukas. 📄 Paper

• Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors. Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Eiji Aramaki, Tomoya Iwakura. 📄 Paper

EMNLP 2025 Findings

• Spelling-out is not Straightforward: LLMs’ Capability of Tokenization from Token to Characters. Tatsuya Hiraoka, Kentaro Inui. 📄 Paper

• How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders. Tatsuro Inaba, Go Kamoda, Kentaro Inui, Masaru Isonuma, Yusuke Miyao, Yohei Oseki, Yu Takagi, and Benjamin Heinzerling. 📄 Paper