Rai, Daking

2 publications

NeurIPS 2025 Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Daking Rai, Samuel Miller, Kevin Moran, Ziyu Yao

AAAI 2023 Explaining Large Language Model-Based Neural Semantic Parsers (Student Abstract) Daking Rai, Yilun Zhou, Bailin Wang, Ziyu Yao