3 papers
cs.LG2025
LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
Chongyu Fan, Changsheng Wang, Yancheng Huang +2
Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model…
cs.CL2025
Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments
Abhirup Chakravarty, Mark Brenchley, Trevor Breakspear +2
A key ethical challenge in Automated Essay Scoring (AES) is ensuring that scores are only released when they meet high reliability standards. Confidence modelling addresses this by…
cs.CL2025
Hierarchical Contextual Manifold Alignment for Structuring Latent Representations in Large Language Models
Meiquan Dong, Haoran Liu, Yan Huang +3
The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional…