The Benefits and Risks of Transductive Approaches for AI Fairness

M Razzak, A Kirsch, Y Gal - arxiv preprint arxiv:2406.12011, 2024 - arxiv.org
Recently, transductive learning methods, which leverage holdout sets during training, have
gained popularity for their potential to improve speed, accuracy, and fairness in machine …

Dynamic Skill Adaptation for Large Language Models

J Chen, D Yang - arxiv preprint arxiv:2412.19361, 2024 - arxiv.org
We present Dynamic Skill Adaptation (DSA), an adaptive and dynamic framework to adapt
novel and complex skills to Large Language Models (LLMs). Compared with previous work …