- Improving Informativeness for Retrieval Augmentation Generation via Reward Modeling
- LocateBench: Evaluating the Locating Ability of Vision Language Models
- Pelican Soup Framework: A Theoretical Framework for Language Model Capabilities
- On Retrieval Augmentation and the Limitations of Language Model Training
- The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining
- On a Benefit of Mask Language Modeling: The Robustness to Simplicity Bias
- Breaking Down Multilingual Machine Translation
- Relating Neural Text Degeneration to Exposure Bias
- Improving Dialogue State Tracking by Joint Slot Modeling
- Are you doing what I say? On modalities alignment in ALFRED
- An Empirical Study of Content Understanding in Conversational Question Answering
- Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems
- Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer
- RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
Research Experience
- Applied Scientist Intern at Amazon Seattle with Kevin Small (Summer 2024)
- Summer Intern at Reka AI with Mikel Artetxe (Summer 2023)
- Applied Scientist Intern at Amazon Seattle with Markus Dreyer (Summer 2022)
Education
PhD student at the University of Southern California, advised by Prof. Dani Yogatama; previously studied at Carnegie Mellon University (CMU) and National Taiwan University (NTU), advised by Prof. Yun-Nung (Vivian) Chen.
Background
Research interest is about assessing and mitigating the limitations of language models. Previously, stayed for a while at Carnegie Mellon University (CMU) and National Taiwan University (NTU).