Subin Lee — accepted AI-conference papers

2024

ExpertQA: Expert-Curated Questions and Attributed Answers

Chaitanya Malaviya, Subin Lee, Sihao Chen, Elizabeth Sieber, Mark Yatskar, Dan Roth

NAACL 2024long

As language models are adopted by a more sophisticated and diverse set of users, the importance of guaranteeing that they provide factually correct information supported by verifiable sources is critical across fields of study. This is especially the case for high-stakes fields, such as medicine and…

Cited by 81 Source ↗PDF ↗code ↗Scholar ↗

2024

What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perception

Chaitanya Malaviya, Subin Lee, Dan Roth, Mark Yatskar

NAACL 2024long

Eliciting feedback from end users of NLP models can be beneficial for improving models. However, how should we present model responses to users so they are most amenable to be corrected from user feedback? Further, what properties do users value to understand and trust responses? We answer these que…

Cited by 2 Source ↗PDF ↗Scholar ↗