Yusuke Sakai

84 papers A* 6A 1B 1Misc 1Journal 42Unranked 33
YearRankTypeTitle / Venue / Authors
2026 — conf
"Yuki Gets Sushi, David Gets Steak?": Uncovering Gender and Racial Biases in LLM-Based Meal Recommendations.
EACL (Volume 1: Long Papers)
Xuefeng Wei, Xuan Zhou, Yusuke Sakai, Taro Watanabe
2026 — conf
Cosine Similarity as Logits?: A Scalable Knowledge Probe Using Embedding Vectors from Generative Language Models.
EACL (Volume 1: Long Papers)
Tomoyuki Jinno, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2026 — conf
Diagnosing Vision Language Models' Perception by Leveraging Human Methods for Color Vision Deficiencies.
EACL (Volume 1: Long Papers)
Kazuki Hayashi, Shintaro Ozaki, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2026 J jnl
Domain Translation with Monolingual Lexical Distribution.
Trans. Mach. Learn. Res.
Yusuke Sakai, Zhi Qu, Hidetaka Kamigaito, Taro Watanabe, Xiaojiang Liu
2026 J jnl
Grammatical Error Correction Evaluation by Optimally Transporting Edit Representation.
CoRR
Takumi Goto, Yusuke Sakai, Taro Watanabe
2026 — conf
Hacking Neural Evaluation Metrics with Single Text.
EACL (Volume 2: Short Papers)
Hiroyuki Deguchi, Katsuki Chousa, Yusuke Sakai
2026 J jnl
HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences.
CoRR
Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2026 J jnl
Rethinking the Evaluation Methods of LLMs' Grammatical Knowledge.
J. Nat. Lang. Process.
Yusuke Ide, Yuto Nishida, Justin Vasselli, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2026 J jnl
StructLens: A Structural Lens for Language Models via Maximum Spanning Trees.
CoRR
Haruki Sakajo, Frederikus Hudi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2026 J jnl
The Wisdom of Many Queries: Complexity-Diversity Principle for Dense Retriever Training.
CoRR
Xincan Feng, Noriki Nishida, Yusuke Sakai, Yuji Matsumoto
2026 — conf
Toward Automatic Delegation Extraction in Japanese Law.
EACL (Industry Track)
Tsuyoshi Fujita, Yuya Sawada, Yusuke Sakai, Taro Watanabe
2026 — conf
Towards Singable Lyrics Translation Using Large Language Models.
EACL (Student Research Workshop)
Liu Hanze, Yusuke Sakai, Taro Watanabe
2026 — conf
entity-linkings: A Unified Library for Entity Linking.
EACL (System Demonstrations)
Yuya Sawada, Tsuyoshi Fujita, Yusuke Sakai, Taro Watanabe
2025 — conf
AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising.
NAACL (Long Papers)
Peinan Zhang, Yusuke Sakai, Masato Mita, Hiroki Ouchi, Taro Watanabe
2025 — conf
Agreement-Constrained Probabilistic Minimum Bayes Risk Decoding.
IJCNLP-AACL (Short Papers)
Koki Natsumi, Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
Agreement-Constrained Probabilistic Minimum Bayes Risk Decoding.
CoRR
Koki Natsumi, Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 — conf
BQA: Body Language Question Answering Dataset for Video Large Language Models.
ACL (2)
Shintaro Ozaki, Kazuki Hayashi, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 — conf
BannerBench: Benchmarking Vision Language Models for Multi-Ad Selection with Human Preferences.
EMNLP (Findings)
Hiroto Otake, Peinan Zhang, Yusuke Sakai, Masato Mita, Hiroki Ouchi, Taro Watanabe
2025 J jnl
Can Impressions of Music be Extracted from Thumbnail Images?
CoRR
Takashi Harada, Takehiro Motomitsu, Katsuhiko Hayashi, Yusuke Sakai, Hidetaka Kamigaito
2025 J jnl
Cross-Era Evaluation of Language Models for Location Referring Expression Extraction.
J. Nat. Lang. Process.
Ayuki Katayama, Shohei Higashiyama, Hiroki Ouchi, Yusuke Sakai, Ayano Takeuchi, Ryo Bando, Yuta Hashimoto, Toshinobu Ogiso, Taro Watanabe
2025 J jnl
Diagnosing Vision Language Models' Perception by Leveraging Human Methods for Color Vision Deficiencies.
CoRR
Kazuki Hayashi, Shintaro Ozaki, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 — conf
Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries.
ACL (Findings)
Haruki Sakajo, Yusuke Ide, Justin Vasselli, Yusuke Sakai, Yingtao Tian, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries.
CoRR
Haruki Sakajo, Yusuke Ide, Justin Vasselli, Yusuke Sakai, Yingtao Tian, Hidetaka Kamigaito, Taro Watanabe
2025 — conf
Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding.
ACL (1)
Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai, Katsuhiko Hayashi, Taro Watanabe
2025 J jnl
Hacking Neural Evaluation Metrics with Single Hub Text.
CoRR
Hiroyuki Deguchi, Katsuki Chousa, Yusuke Sakai
2025 — conf
How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments.
NAACL (Long Papers)
Yusuke Ide, Yuto Nishida, Justin Vasselli, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 — conf
IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator.
ACL (Findings)
Yusuke Sakai, Takumi Goto, Taro Watanabe
2025 J jnl
IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator.
CoRR
Yusuke Sakai, Takumi Goto, Taro Watanabe
2025 B conf
IRR: Image Review Ranking Framework for Evaluating Vision-Language Models.
COLING
Kazuki Hayashi, Kazuma Onishi, Toma Suzuki, Yusuke Ide, Seiji Gobara, Shigeki Saito, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2025 — conf
Investigating Omission as a Latency Reduction Strategy in Simultaneous Speech Translation.
IJCNLP-AACL (Findings)
Mana Makinae, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
Investigation of the Inference Capabilities and Memorization of Pre-trained Language Models.
J. Nat. Lang. Process.
Yusuke Sakai
2025 A* conf
Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark.
EMNLP
Chihiro Taguchi, Seng Mai, Keita Kurabe, Yusuke Sakai, Georgina Agyei, Soudabeh Eslami, David Chiang
2025 J jnl
Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark.
CoRR
Chihiro Taguchi, Seng Mai, Keita Kurabe, Yusuke Sakai, Georgina Agyei, Soudabeh Eslami, David Chiang
2025 A* conf
LoCt-Instruct: An Automatic Pipeline for Constructing Datasets of Logical Continuous Instructions.
EMNLP
Hongyu Sun, Yusuke Sakai, Haruki Sakajo, Shintaro Ozaki, Kazuki Hayashi, Hidetaka Kamigaito, Taro Watanabe
2025 A* conf
Multilingual Dialogue Generation and Localization with Dialogue Act Scripting.
EMNLP
Justin Vasselli, Eunike Andriani Kardinata, Yusuke Sakai, Taro Watanabe
2025 J jnl
Multilingual Dialogue Generation and Localization with Dialogue Act Scripting.
CoRR
Justin Vasselli, Eunike Andriani Kardinata, Yusuke Sakai, Taro Watanabe
2025 — conf
Reliability Crisis of Reference-free Metrics for Grammatical Error Correction.
EMNLP (Findings)
Takumi Goto, Yusuke Sakai, Taro Watanabe
2025 J jnl
Reliability Crisis of Reference-free Metrics for Grammatical Error Correction.
CoRR
Takumi Goto, Yusuke Sakai, Taro Watanabe
2025 — conf
Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions.
NAACL (Student Research Workshop)
Toma Suzuki, Ayuki Katayama, Seiji Gobara, Ryo Tsujimoto, Hibiki Nakatani, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 — conf
Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?
ACL (2)
Takumi Goto, Yusuke Sakai, Taro Watanabe
2025 J jnl
Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?
CoRR
Takumi Goto, Yusuke Sakai, Taro Watanabe
2025 — conf
Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability.
ACL (1)
Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability.
CoRR
Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair.
J. Nat. Lang. Process.
Yusuke Sakai
2025 A* conf
SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala.
EMNLP
Ashmari Pramodya, Nirasha Nelki, Heshan Shalinda, Chamila Liyanage, Yusuke Sakai, Randil Pushpananda, Ruvan Weerasinghe, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala.
CoRR
Ashmari Pramodya, Nirasha Nelki, Heshan Shalinda, Chamila Liyanage, Yusuke Sakai, Randil Pushpananda, Ruvan Weerasinghe, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation.
CoRR
Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Jingun Kwon, Hidetaka Kamigaito, Katsuhiko Hayashi, Manabu Okumura, Taro Watanabe
2025 — conf
Tonguescape: Exploring Language Models Understanding of Vowel Articulation.
NAACL (Long Papers)
Haruki Sakajo, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
Tonguescape: Exploring Language Models Understanding of Vowel Articulation.
CoRR
Haruki Sakajo, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 J jnl
Toward the Final Piece of My Doctoral Thesis.
J. Nat. Lang. Process.
Yusuke Sakai
2025 — conf
Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models.
NAACL (Findings)
Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2025 — conf
Translating Movie Subtitles by Large Language Models using Movie-meta Information.
ACL (4)
Ashmari Pramodya, Yusuke Sakai, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe
2025 Misc conf
Visual Priming Effect on Large-scale Vision Language Models.
RANLP
Daiki Yoshida, Haruki Sakajo, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2025 J jnl
Vowel Articulation and Tongue Position in Vision Language Models.
J. Nat. Lang. Process.
Haruki Sakajo, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2025 — conf
gec-metrics: A Unified Library for Grammatical Error Correction Evaluation.
ACL (3)
Takumi Goto, Yusuke Sakai, Taro Watanabe
2025 J jnl
gec-metrics: A Unified Library for Grammatical Error Correction Evaluation.
CoRR
Takumi Goto, Yusuke Sakai, Taro Watanabe
2024 J jnl
AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising.
CoRR
Peinan Zhang, Yusuke Sakai, Masato Mita, Hiroki Ouchi, Taro Watanabe
2024 J jnl
Artwork Explanation in Large-scale Vision Language Models.
CoRR
Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2024 J jnl
BQA: Body Language Question Answering Dataset for Video Large Language Models.
CoRR
Shintaro Ozaki, Kazuki Hayashi, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2024 — conf
Centroid-Based Efficient Minimum Bayes Risk Decoding.
ACL (Findings)
Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe, Hideki Tanaka, Masao Utiyama
2024 J jnl
Centroid-Based Efficient Minimum Bayes Risk Decoding.
CoRR
Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe, Hideki Tanaka, Masao Utiyama
2024 — conf
Document-level Translation with LLM Reranking: Team-J at WMT 2024 General Translation Task.
WMT
Keito Kudo, Hiroyuki Deguchi, Makoto Morishita, Ryo Fujii, Takumi Ito, Shintaro Ozaki, Koki Natsumi, Kai Sato, Kazuki Yano, Ryosuke Takahashi, Subaru Kimura, Tomomasa Hara, Yusuke Sakai, Jun Suzuki
2024 — conf
Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
NAACL-HLT
Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2024 J jnl
Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
J. Nat. Lang. Process.
Yusuke Sakai
2024 J jnl
Evaluating Image Review Ability of Vision Language Models.
CoRR
Shigeki Saito, Kazuki Hayashi, Yusuke Ide, Yusuke Sakai, Kazuma Onishi, Toma Suzuki, Seiji Gobara, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2024 J jnl
How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments.
CoRR
Yusuke Ide, Yuto Nishida, Miyu Oba, Yusuke Sakai, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe
2024 J jnl
Investigation of the Inference Capabilities and Memorization of Pre-trained Language Models.
J. Nat. Lang. Process.
Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2024 A* conf
Simul-MuST-C: Simultaneous Multilingual Speech Translation Corpus Using Large Language Model.
EMNLP
Mana Makinae, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2024 A* conf
Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair.
EMNLP
Yusuke Sakai, Mana Makinae, Hidetaka Kamigaito, Taro Watanabe
2024 J jnl
Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair.
CoRR
Yusuke Sakai, Mana Makinae, Hidetaka Kamigaito, Taro Watanabe
2024 J jnl
Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding.
CoRR
Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai, Katsuhiko Hayashi, Taro Watanabe
2024 J jnl
Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates.
CoRR
Yusuke Sakai, Adam Nohejl, Jiangnan Hang, Hidetaka Kamigaito, Taro Watanabe
2024 — conf
Towards Artwork Explanation in Large-scale Vision Language Models.
ACL (Short Papers)
Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2024 J jnl
Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models.
CoRR
Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2024 — conf
mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans.
ACL (Findings)
Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2024 J jnl
mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans.
CoRR
Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2024 — conf
mbrs: A Library for Minimum Bayes Risk Decoding.
EMNLP (System Demonstrations)
Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2024 J jnl
mbrs: A Library for Minimum Bayes Risk Decoding.
CoRR
Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
2023 J jnl
Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
CoRR
Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
2023 — conf
NAIST-NICT WMT'23 General MT Task Submission.
WMT
Hiroyuki Deguchi, Kenji Imamura, Yuto Nishida, Yusuke Sakai, Justin Vasselli, Taro Watanabe
2023 A conf
Universal Automatic Phonetic Transcription into the International Phonetic Alphabet.
INTERSPEECH
Chihiro Taguchi, Yusuke Sakai, Parisa Haghani, David Chiang
2023 J jnl
Universal Automatic Phonetic Transcription into the International Phonetic Alphabet.
CoRR
Chihiro Taguchi, Yusuke Sakai, Parisa Haghani, David Chiang
2022 — conf
NAIST-NICT-TIT WMT22 General MT Task Submission.
WMT
Hiroyuki Deguchi, Kenji Imamura, Masahiro Kaneko, Yuto Nishida, Yusuke Sakai, Justin Vasselli, Huy Hien Vu, Taro Watanabe
2021 — conf
Transliteration for Low-Resource Code-Switching Texts: Building an Automatic Cyrillic-to-Latin Converter for Tatar.
CALCS@NAACL
Chihiro Taguchi, Yusuke Sakai, Taro Watanabe