5 papers
Language-Induced Priors for Domain Adaptation
Qiyuan Chen, Jiayu Zhou, Raed Al Kontar
Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant source domains from irrelevant…
Dual Debiasing for Noisy In-Context Learning for Text Generation
Siqi Liang, Sumyeong Ahn, Paramveer S. Dhillon +1
In context learning (ICL) relies heavily on high quality demonstrations drawn from large annotated corpora. Existing approaches detect noisy annotations by ranking local perplexiti…
Distributed In-Context Learning under Non-IID Among Clients
Siqi Liang, Sumyeong Ahn, Jiayu Zhou
Advancements in large language models (LLMs) have shown their effectiveness in multiple complicated natural language reasoning tasks. A key challenge remains in adapting these mode…
Augmented Risk Prediction for the Onset of Alzheimer's Disease from Electronic Health Records with Large Language Models
Jiankun Wang, Sumyeong Ahn, Taykhoom Dalal +7
Alzheimer's disease (AD) is the fifth-leading cause of death among Americans aged 65 and older. Screening and early detection of AD and related dementias (ADRD) are critical for ti…
Large Language Models in Medical Term Classification and Unexpected Misalignment Between Response and Reasoning
Xiaodan Zhang, Sandeep Vemulapalli, Nabasmita Talukdar +11
This study assesses the ability of state-of-the-art large language models (LLMs) including GPT-3.5, GPT-4, Falcon, and LLaMA 2 to identify patients with mild cognitive impairment (…