<ul><li>Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations</li><li>Conventional recommendation systems (RSs) often overlook the needs of diverse user populations, leading to performance disparities and reduced robustness to sub-populations.</li><li>A hybrid task allocation framework is proposed to promote social good and serve all user groups equitably by efficiently adapting large language models (LLMs).</li><li>The framework involves identifying weak and inactive users, using an in-context learning approach, and evaluating the performance on real-world datasets with positive results.</li></ul>

Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations

Discover more