3 papers
cs.LG2025
Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs
James Flemings, Haosheng Gan, Hongyi Li +2
In-context learning (ICL) has shown promising improvement in downstream task adaptation of LLMs by augmenting prompts with relevant input-output examples (demonstrations). However,…
cs.LG2025
Learning Hyperplane Tree: A Piecewise Linear and Fully Interpretable Decision-making Framework
Hongyi Li, Jun Xu, William Ward Armstrong
This paper introduces a novel tree-based model, Learning Hyperplane Tree (LHT), which outperforms state-of-the-art (SOTA) tree models for classification tasks on several public dat…
cs.CR2024
JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
Hongyi Li, Jiawei Ye, Jie Wu +3
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipu…