1.2k citations · 1.8k across the 35 of their papers we have counts for
5 papers · 2 filters
What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perception
Chaitanya Malaviya, Subin Lee, Dan Roth +1
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 corr…
Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck
Josh Magnus Ludan, Qing Lyu, Yue Yang +3
Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose…
ExpertQA: Expert-Curated Questions and Attributed Answers
Chaitanya Malaviya, Subin Lee, Sihao Chen +3
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 verifia…
Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering
Xingyu Fu, Ben Zhou, Sihao Chen +2
Recent advances in multimodal large language models (LLMs) have shown extreme effectiveness in visual question answering (VQA). However, the design nature of these end-to-end model…
AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreference
Yuewei Yuan, Chaitanya Malaviya, Mark Yatskar
Given a sentence "Abby told Brittney that she upset Courtney", one would struggle to understand who "she" refers to, and ask for clarification. However, if the word "upset" were re…