3 citations · 13 across the 17 of their papers we have counts for
10 papers · 1 filter
Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration
Ruochen Jin, Zhanliang Wang, Zongyu Dai +2
Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated. Traditional post-hoc temperature scaling is inherently domain-dependent: a temper…
Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
Parvin Nazari, Bojian Hou, Davoud Ataee Tarzanagh +2
Online bilevel optimization (OBO) is a powerful framework for machine learning problems where both outer and inner objectives evolve over time, requiring dynamic updates. Current O…
Fair CCA for Fair Representation Learning: An ADNI Study
Bojian Hou, Zhanliang Wang, Zhuoping Zhou +6
Canonical correlation analysis (CCA) is a technique for finding correlations between different data modalities and learning low-dimensional representations. As fairness becomes cru…
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
Jiancong Xiao, Bojian Hou, Zhanliang Wang +4
One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: whi…
ICAFS: Inter-Client-Aware Feature Selection for Vertical Federated Learning
Ruochen Jin, Boning Tong, Shu Yang +2
Vertical federated learning (VFL) enables a paradigm for vertically partitioned data across clients to collaboratively train machine learning models. Feature selection (FS) plays a…
MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance
Jia Xu, Tianyi Wei, Bojian Hou +7
We introduce MentalChat16K, an English benchmark dataset combining a synthetic mental health counseling dataset and a dataset of anonymized transcripts from interventions between B…
Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models
Joseph Lee, Shu Yang, Jae Young Baik +8
Predicting phenotypes with complex genetic bases based on a small, interpretable set of variant features remains a challenging task. Conventionally, data-driven approaches are util…
Fairness-Aware Estimation of Graphical Models
Zhuoping Zhou, Davoud Ataee Tarzanagh, Bojian Hou +2
This paper examines the issue of fairness in the estimation of graphical models (GMs), particularly Gaussian, Covariance, and Ising models. These models play a vital role in unders…
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
Ruochen Jin, Bojian Hou, Jiancong Xiao +2
In recent years, task arithmetic has garnered increasing attention. This approach edits pre-trained models directly in weight space by combining the fine-tuned weights of various t…
Fair Canonical Correlation Analysis
Zhuoping Zhou, Davoud Ataee Tarzanagh, Bojian Hou +5
This paper investigates fairness and bias in Canonical Correlation Analysis (CCA), a widely used statistical technique for examining the relationship between two sets of variables.…