6 citations · 15 across the 6 of their papers we have counts for
7 papers
DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression
Yiheng Su, Junyi Jessy Li, Matthew Lease
While work on LLM-based regression has largely focused on scalar prediction, multi-output text regression remains less explored. We present DualView, a parameter-efficient approach…
PIE: Performance Interval Estimation for Free-Form Generation Tasks
Chi-Yang Hsu, Alexander Braylan, Yiheng Su +2
Confidence estimation infers a probability for whether each model output is correct or not. While predicting such binary correctness is sensible for tasks with exact answers, free-…
Rhetorical XAI: Explaining AI's Benefits as well as its Use via Rhetorical Design
Houjiang Liu, Yiheng Su, Matthew Lease
We explore potential benefits of incorporating Rhetorical Design into the design of Explainable Artificial Intelligence (XAI) systems. While XAI is traditionally framed around expl…
Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation
Terrence Neumann, Sooyong Lee, Maria De-Arteaga +2
The pervasive spread of misinformation and disinformation poses a significant threat to society. Professional fact-checkers play a key role in addressing this threat, but the vast…
A General Model for Aggregating Annotations Across Simple, Complex, and Multi-Object Annotation Tasks
Alexander Braylan, Madalyn Marabella, Omar Alonso +1
Human annotations are vital to supervised learning, yet annotators often disagree on the correct label, especially as annotation tasks increase in complexity. A strategy to improve…
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
Luis Oala, Manil Maskey, Lilith Bat-Leah +35
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure developm…
Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data
Yiheng Su, Junyi Jessy Li, Matthew Lease
Can we preserve the accuracy of neural models while also providing faithful explanations of model decisions to training data? We propose a "wrapper box'' pipeline: training a neura…