2 citations · 2 across the 4 of their papers we have counts for
5 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…
RELISH: LLM REgression with a Latent Iterative State Head
Yiheng Su, Matthew Lease
We present RELISH (REgression with a Latent Iterative State Head), a novel, lightweight architecture designed for text regression with large language models. Rather than decoding n…
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…
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…