陣内 佑

Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport. 

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 28260-28279 2025年  

Theoretical Guarantees for Minimum Bayes Risk Decoding. 

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 16262-16284 2025年  

Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales. 

Findings of the Association for Computational Linguistics 16124-16146 2025年  

Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment. 

NAACL (Long Papers) 9321-9347 2025年  

On the True Distribution Approximation of Minimum Bayes-Risk Decoding. 

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Short Papers 459-468 2024年  

Model-Based Minimum Bayes Risk Decoding for Text Generation. 

Forty-first International Conference on Machine Learning(ICML) 2024年  

Filtered Direct Preference Optimization. 

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing(EMNLP) 22729-22770 2024年  

Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding. 

Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting 8547-8566 2024年  

Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding. 

Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting 8494-8525 2024年  

Exploration in Reinforcement Learning with Deep Covering Options. 

8th International Conference on Learning Representations(ICLR) 2020年  

State Abstraction as Compression in Apprenticeship Learning. 

The Thirty-Third AAAI Conference on Artificial Intelligence(AAAI) 3134-3142 2019年  

Learning to Avoid Dominated Action Sequences in Planning for Black-Box Domains. 

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence(AAAI) 4943-4944 2017年