Full List of Publications and Manuscripts
2024
BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
AISTATS'24 Paper
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
ICLR'24 Paper
RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records
POLYIE: A Dataset of Information Extraction from Polymer Material Scientific Literature
HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification
TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance
arXiv'24 Paper
EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records
2023
How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Ranking
Knowledge-Infused Prompting Improves Clinical Text Generation with Large Language Models
SyntheticData4ML@NeurIPS'23 Paper
Retrieval-Augmented Large Language Models for Adolescent Idiopathic Scoliosis Patients in Shared Decision-Making
BCB'23 (Best Paper) Paper
DF2: Distribution-Free Decision-Focused Learning
arXiv'23 Paper
AdaPlanner: Adaptive Planning from Feedback with Language Models
ToolQA: A Dataset for LLM Question Answering with External Tools
Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
G-STO: Sequential Main Shopping Intention Detection via Graph-Regularized Stochastic Transformer
CIKM'23 Paper
Autoregressive Diffusion Model for Graph Generation
ICML'23 Paper
MUBen: Benchmarking the Uncertainty of Pre-Trained Models for Molecular Property Prediction
DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling
ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval
End-to-End Stochastic Optimization with Energy-Based Model
2022
ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select