Tatsuya Hiraoka

41 papers A* 1B 2C 1Journal 25Unranked 12

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Sycophancy Hides Linearly in the Attention Heads. EACL (Volume 1: Long Papers) Rifo Ahmad Genadi, Munachiso Nwadike, Nurdaulet Mukhituly, Tatsuya Hiraoka, Hilal AlQuabeh, Kentaro Inui
2026	J	`jnl`	Sycophancy Hides Linearly in the Attention Heads. CoRR Rifo Ahmad Genadi, Munachiso Nwadike, Nurdaulet Mukhituly, Hilal AlQuabeh, Tatsuya Hiraoka, Kentaro Inui
2025	J	`jnl`	Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM. CoRR Seiya Ishikura, Hiroaki Yamada, Tatsuya Hiraoka, Hiroaki Yamada, Takenobu Tokunaga
2025	J	`jnl`	Bit-level BPE: Below the byte boundary. CoRR Sangwhan Moon, Tatsuya Hiraoka, Naoaki Okazaki
2025	J	`jnl`	Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance. CoRR Shintaro Ozaki, Tatsuya Hiraoka, Hiroto Otake, Hiroki Ouchi, Masaru Isonuma, Benjamin Heinzerling, Kentaro Inui, Taro Watanabe, Yusuke Miyao, Yohei Oseki, Yu Takagi
2025	A*	`conf`	Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors. EMNLP Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Eiji Aramaki, Tomoya Iwakura
2025	J	`jnl`	Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors. CoRR Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Eiji Aramaki, Tomoya Iwakura
2025	—	`conf`	Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles. ACL (1) Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Benjamin Heinzerling, Velibor Bojkovic, Hilal AlQuabeh, Martin Takác, Kentaro Inui
2025	J	`jnl`	Number Representations in LLMs: A Computational Parallel to Human Perception. CoRR H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic, Tatsuya Hiraoka, Ahmed Oumar El-Shangiti, Munachiso Nwadike, Kentaro Inui
2025	J	`jnl`	RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles. CoRR Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Velibor Bojkovic, Benjamin Heinzerling, Hilal Alqaubeh, Martin Takác, Kentaro Inui
2025	—	`conf`	Repetition Neurons: How Do Language Models Produce Repetitions? NAACL (Short Papers) Tatsuya Hiraoka, Kentaro Inui
2025	—	`conf`	Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters. EMNLP (Findings) Tatsuya Hiraoka, Kentaro Inui
2025	J	`jnl`	Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters. CoRR Tatsuya Hiraoka, Kentaro Inui
2025	B	`conf`	SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization. COLING Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Tomoya Iwakura
2025	—	`conf`	The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces. NAACL (Short Papers) Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui
2025	—	`conf`	Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning. IJCNLP-AACL (long papers) Nhi Hoai Doan, Tatsuya Hiraoka, Kentaro Inui
2025	J	`jnl`	Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning. CoRR Nhi Hoai Doan, Tatsuya Hiraoka, Kentaro Inui
2025	J	`jnl`	VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource Languages. CoRR Jesse Atuhurra, Iqra Ali, Tomoya Iwakura, Hidetaka Kamigaito, Tatsuya Hiraoka
2024	J	`jnl`	An Analysis of BPE Vocabulary Trimming in Neural Machine Translation. CoRR Marco Cognetta, Tatsuya Hiraoka, Naoaki Okazaki, Rico Sennrich, Yuval Pinter
2024	J	`jnl`	Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models. CoRR Jesse Atuhurra, Iqra Ali, Tatsuya Hiraoka, Hidetaka Kamigaito, Tomoya Iwakura, Taro Watanabe
2024	J	`jnl`	Knowledge of Pretrained Language Models on Surface Information of Tokens. CoRR Tatsuya Hiraoka, Naoaki Okazaki
2024	J	`jnl`	LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs. CoRR Akiko Aizawa, Eiji Aramaki, Bowen Chen, Fei Cheng, Hiroyuki Deguchi, Rintaro Enomoto, Kazuki Fujii, Kensuke Fukumoto, Takuya Fukushima, Namgi Han, Yuto Harada, Chikara Hashimoto, Tatsuya Hiraoka, Shohei Hisada, Sosuke Hosokawa, Lu Jie, Keisuke Kamata, Teruhito Kanazawa, Hiroki Kanezashi, Hiroshi Kataoka, Satoru Katsumata, Daisuke Kawahara, Seiya Kawano, Atsushi Keyaki, Keisuke Kiryu, Hirokazu Kiyomaru, Takashi Kodama, Takahiro Kubo, Yohei Kuga, Ryoma Kumon, Shuhei Kurita, Sadao Kurohashi, Conglong Li, Taiki Maekawa, Hiroshi Matsuda, Yusuke Miyao, Kentaro Mizuki, Sakae Mizuki, Yugo Murawaki, Ryo Nakamura, Taishi Nakamura, Kouta Nakayama, Tomoka Nakazato, Takuro Niitsuma, Jiro Nishitoba, Yusuke Oda, Hayato Ogawa, Takumi Okamoto, Naoaki Okazaki, Yohei Oseki, Shintaro Ozaki, Koki Ryu, Rafal Rzepka, Keisuke Sakaguchi, Shota Sasaki, Satoshi Sekine, Kohei Suda, Saku Sugawara, Issa Sugiura, Hiroaki Sugiyama, Hisami Suzuki, Jun Suzuki, Toyotaro Suzumura, Kensuke Tachibana, Yu Takagi, Kyosuke Takami, Koichi Takeda, Masashi Takeshita, Masahiro Tanaka, Kenjiro Taura, Arseny Tolmachev, Nobuhiro Ueda, Zhen Wan, Shuntaro Yada, Sakiko Yahata, Yuya Yamamoto, Yusuke Yamauchi, Hitomi Yanaka, Rio Yokota, Koichiro Yoshino
2024	J	`jnl`	Repetition Neurons: How Do Language Models Produce Repetitions? CoRR Tatsuya Hiraoka, Kentaro Inui
2024	J	`jnl`	Roles and Challenges of Industry, Academia, and Government for Natural Language Processing in the Generative Artificial Intelligence Era: An NLP2024 Workshop. J. Nat. Lang. Process. Hiroki Iida, Tomoya Iwakura, Jungo Kasai, Noriyuki Kojima, Mamoru Komachi, Kanako Komiya, Akihiro Tamura, Takashi Ninomiya, Tatsuya Hiraoka, Sakae Mizuki
2024	J	`jnl`	SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization. CoRR Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Tomoya Iwakura
2024	J	`jnl`	The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces. CoRR Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui
2023	J	`jnl`	Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing. CoRR Tatsuya Hiraoka, Tomoya Iwakura
2023	J	`jnl`	Tokenization Tractability for Human and Machine Learning Model: An Annotation Study. CoRR Tatsuya Hiraoka, Tomoya Iwakura
2023	C	`conf`	Vocabulary Replacement in SentencePiece for Domain Adaptation. PACLIC Teruno Kajiura, Shiho Takano, Tatsuya Hiraoka, Kimio Kuramitsu
2022	—	`conf`	Joint Entity and Relation Extraction Based on Table Labeling Using Convolutional Neural Networks. SPNLP@ACL Youmi Ma, Tatsuya Hiraoka, Naoaki Okazaki
2022	B	`conf`	MaxMatch-Dropout: Subword Regularization for WordPiece. COLING Tatsuya Hiraoka
2022	J	`jnl`	MaxMatch-Dropout: Subword Regularization for WordPiece. CoRR Tatsuya Hiraoka
2022	J	`jnl`	Recurrent Neural Hidden Markov Model for High-order Transition. ACM Trans. Asian Low Resour. Lang. Inf. Process. Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki
2022	—	`conf`	Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation. ACL (Findings) Sho Takase, Tatsuya Hiraoka, Naoaki Okazaki
2022	J	`jnl`	Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation. CoRR Sho Takase, Tatsuya Hiraoka, Naoaki Okazaki
2022	—	`conf`	Word-level Perturbation Considering Word Length and Compositional Subwords. ACL (Findings) Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki
2021	—	`conf`	Joint Optimization of Tokenization and Downstream Model. ACL/IJCNLP (Findings) Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki
2021	J	`jnl`	Joint Optimization of Tokenization and Downstream Model. CoRR Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki
2020	J	`jnl`	Named Entity Recognition and Relation Extraction using Enhanced Table Filling by Contextualized Representations. CoRR Youmi Ma, Tatsuya Hiraoka, Naoaki Okazaki
2020	—	`conf`	Optimizing Word Segmentation for Downstream Task. EMNLP (Findings) Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki
2019	—	`conf`	Stochastic Tokenization with a Language Model for Neural Text Classification. ACL (1) Tatsuya Hiraoka, Hiroyuki Shindo, Yuji Matsumoto