Hi, I’m Yenhsiang Wang (王彥翔). Currently as Research Assitant at the Natural Language Processing Lab at National Chung Hsing University. My master’s research is advised by Professor Yao-Chang Fan.

My recent research and projects are as follows include Natural Language Processing and Machine Learning, including but not limited to:

• Exploring how LLMs can enhance translation for Indigenous languages ​​by leveraging Chain-of-Thought reasoning by giving relevant patterns by sentence retrieval.
• Researching on the performance of Sparse embedding, Dense embedding, and LLM query expansion in specific domain retrieval.

Download my CV here

Currently seeking for PhD opportunities starting from 2025 Fall.

Research Interests

• Reliable and robust integration of effective retrievers and large language models.
• Interpretability on Large Language Models.

I am interested in enhancing the interpretability of model mechanisms and their understanding of human intentions, as well as in providing more accurate and reliable retrieval methods for Large Language Models.

News

• 11/2024: I co-taught a tutorial on Retrieval-Augmented Language Models at ROCLING 2024. Slides are available on our website.
• 11/2024: Our paper, which constructs a Cross-Lingual Retrieval Dataset in the Taiwan Legal domain, was nominated for Best Paper at ROCLING 2024.
• 08/2024 Our papaer Learning-From-Mistakes Prompting for Indigenous Language Translation was accepted to the ACL LoResMT 2024.

Publications

2024

• A Cross-Lingual Statutory Article Retrieval Dataset for Taiwan Legal Studies Yen-Hsiang Wang , Feng-Dian Su, Tzu-Yu Yeh, Yao-Chung Fan In ROCLING 2024. [pdf]

• Learning-From-Mistakes Prompting for Indigenous Language Translation You-Cheng Liao, Chen-Jui Yu, Chi-Yi Lin, He-Feng Yun, Yen-Hsiang Wang, Hsiao-Min Li, Yao-Chung Fan. In ACL LoResMT 2024. [pdf]

2023

• Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation Xingdi Yuan, Tong Wang, Yen-Hsiang Wang, Emery Fine, Rania Abdelghani, Pauline Lucas, Hélène Sauzéon, Pierre-Yves Oudeyer. In ACL 2023 Findings. [pdf]

• GPT-3-driven pedagogical agents for training children’s curious question-asking skills Rania Abdelghani, Yen-Hsiang Wang, Xingdi Yuan, Tong Wang, Pauline Lucas, Hélène Sauzéon, Pierre-Yves Oudeyer. In IJAIED. [pdf]

Service

Reviewer:

• GEM Workshop at EMNLP 2023