9 papers
LLMs on a Budget? Say HOLA
Zohaib Hasan Siddiqui, Jiechao Gao, Ebad Shabbir +4
Running Large Language Models (LLMs) on edge devices is constrained by high compute and memory demands posing a barrier for real-time applications in sectors like healthcare, educa…
CUFG: Curriculum Unlearning Guided by the Forgetting Gradient
Jiaxing Miao, Liang Hu, Qi Zhang +2
As privacy and security take center stage in AI, machine unlearning, the ability to erase specific knowledge from models, has garnered increasing attention. However, existing metho…
A Survey on Progress in LLM Alignment from the Perspective of Reward Design
Miaomiao Ji, Yanqiu Wu, Zhibin Wu +4
Reward design plays a pivotal role in aligning large language models (LLMs) with human values, serving as the bridge between feedback signals and model optimization. This survey pr…
COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement
Zhihao Sui, Liang Hu, Jian Cao +3
Large deep learning models have achieved significant success in various tasks. However, the performance of a model can significantly degrade if it is needed to train on datasets wi…
Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
Zhihao Sui, Liang Hu, Jian Cao +4
Machine Unlearning (MU) technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology,…
XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content
Vadivel Abishethvarman, Bhavik Chandna, Pratik Jalan +1
Large Language Models (LLMs) can generate content spanning ideological rhetoric to explicit instructions for violence. However, existing safety evaluations often rely on simplistic…