| 2026 | ACL | Does Self-Consistency Improve the Recall of Encyclopedic Knowledge? | Sho Hoshino, Ukyo Honda, Peinan Zhang |
| 2026 | ACL | BiCSRouter: Bi-Level Cross-System Routing for Utility-Aware LLM Inference. | Keyu Mao, Eiki Murata, Ukyo Honda |
| 2025 | ACL | Exploring Explanations Improves the Robustness of In-Context Learning. | Ukyo Honda, Tatsushi Oka |
| 2025 | EMNLP | Distilling Many-Shot In-Context Learning into a Cheat Sheet. | Ukyo Honda, Soichiro Murakami, Peinan Zhang |
| 2025 | EMNLP | Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts. | Yuu Jinnai, Ukyo Honda |
| 2024 | ACL | Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding. | Yuu Jinnai, Ukyo Honda, Tetsuro Morimura, Peinan Zhang |
| 2024 | COLING | CAMERA³: An Evaluation Dataset for Controllable Ad Text Generation in Japanese. | Go Inoue, Akihiko Kato, Masato Mita, Ukyo Honda, Peinan Zhang |
| 2024 | COLING | A Single Linear Layer Yields Task-Adapted Low-Rank Matrices. | Hwichan Kim, Shota Sasaki, Sho Hoshino, Ukyo Honda |
| 2024 | ICML | Model-Based Minimum Bayes Risk Decoding for Text Generation. | Yuu Jinnai, Tetsuro Morimura, Ukyo Honda, Kaito Ariu, Kenshi Abe |
| 2024 | NAACL | On the True Distribution Approximation of Minimum Bayes-Risk Decoding. | Atsumoto Ohashi, Ukyo Honda, Tetsuro Morimura, Yuu Jinnai |
| 2024 | NAACL | Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation. | Hao Wang, Tetsuro Morimura, Ukyo Honda, Daisuke Kawahara |
| 2023 | WACV | Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning. | Ukyo Honda, Taro Watanabe, Yuji Matsumoto |
| 2022 | PACLIC | Law Retrieval with Supervised Contrastive Learning Using the Hierarchical Structure of Law. | Jungmin Choi, Ukyo Honda, Taro Watanabe, Hiroki Ouchi, Kentaro Inui |
| 2021 | EACL | Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning. | Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe, Yuji Matsumoto |
| 2018 | NAACL | Pruning Basic Elements for Better Automatic Evaluation of Summaries. | Ukyo Honda, Tsutomu Hirao, Masaaki Nagata |