David Anugraha, Shou-Yi Hung, Zilu Tang, En-Shiun Annie Lee, Derry Tanti Wijaya, Genta Indra Winata
Published in ICLR Poster, 2025
We introduce mR3, a massively multilingual, rubric-agnostic reward reasoning model trained on 72 languages.
Hannah Liu, Ethan Yue Heng Cheung, Shou-Yi Hung, Junghyun Min, Syed Mekael Wasti, Runtong Liang, ShiYao Qian, shizhao zheng, Elsie Chan, Ka Ieng Charlotte Lo, Wing Yu Yip, Richard Tzong-Han Tsai, En-Shiun Annie Lee
Published in COLM WMDQS Workshop, 2025
This paper provides a dataset for Sinitic Languages, annotated with Translation Errors
Genta Indra Winata, David Anugraha, Emmy Liu, Alham Fikri Aji, Shou-Yi Hung, Aditya Parashar, Patrick Amadeus Irawan, Ruochen Zhang, Zheng-Xin Yong, Jan Christian Blaise Cruz, Niklas Muennighoff, Seungone Kim, Hanyang Zhao, Sudipta Kar, Kezia Erina Suryoraharjo, M Farid Adilazuarda, En-Shiun Annie Lee, Ayu Purwarianti, Derry Tanti Wijaya, Monojit Choudhury
Published in Arxiv, 2025
This paper provides a systematic way to evaluate dataset submissions, encouraging higher quality datasets to be submitted
Syed Mekael Wasti*, Shou-Yi Hung*, En-Shiun Annie Lee
Published in ACL Demo, 2025
This paper provides an integrated framework that streamlines the translation process, enabling easier data collection procedures and translation pipelines.
David Anugraha, Zilu Tang, Lester James Validad Miranda, Hanyang Zhao, Shou-Yi Hung, Mohammad Rifqi Farhansyah, Garry Kuwanto, Derry Tanti Wijaya, Genta Indra Winata
Published in NeurIPS LLM Evaluation Workshop, 2025
This paper introduces a novel reward modelling framework that is rubric-agnostic
Yun-Hsin Chu, Shuai Zhu, Shou-Yi Hung, Bo-Ting Lin, En-Shiun Annie Lee, Richard Tzong-Han Tsai
Published in NAACL Demo, 2025
This paper presents a framework that utilizes multiple AI models to preserve the endangered language of Taiwanese Hokkien
En-Shiun Annie Lee, Luki Danukarjanto, Sadia Sharmin, Shou-Yi Hung, Sicong Huang, and Tong Su
Published in ACM SIGCSE TS, 2024
This paper analyses different factors of motivation for computer science students across three different levels.