{"ID":2851592,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.19351","arxiv_id":"2510.19351","title":"Learning To Defer To A Population With Limited Demonstrations","abstract":"This paper addresses the critical data scarcity that hinders the practical deployment of learning to defer (L2D) systems to the population. We introduce a context-aware, semi-supervised framework that uses meta-learning to generate expert-specific embeddings from only a few demonstrations. We demonstrate the efficacy of a dual-purpose mechanism, where these embeddings are used first to generate a large corpus of pseudo-labels for training, and subsequently to enable on-the-fly adaptation to new experts at test-time. The experiment results on three different datasets confirm that a model trained on these synthetic labels rapidly approaches oracle-level performance, validating the data efficiency of our approach. By resolving a key training bottleneck, this work makes adaptive L2D systems more practical and scalable, paving the way for human-AI collaboration in real-world environments. To facilitate reproducibility and address implementation details not covered in the main text, we provide our source code and training configurations at https://github.com/nil123532/learning-to-defer-to-a-population-with-limited-demonstrations.","short_abstract":"This paper addresses the critical data scarcity that hinders the practical deployment of learning to defer (L2D) systems to the population. We introduce a context-aware, semi-supervised framework that uses meta-learning to generate expert-specific embeddings from only a few demonstrations. We demonstrate the efficacy o...","url_abs":"https://arxiv.org/abs/2510.19351","url_pdf":"https://arxiv.org/pdf/2510.19351v2","authors":"[\"Nilesh Ramgolam\",\"Gustavo Carneiro\",\"Hsiang-Ting Chen\"]","published":"2025-10-22T08:18:02Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607921,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2851592,"paper_url":"https://arxiv.org/abs/2510.19351","paper_title":"Learning To Defer To A Population With Limited Demonstrations","repo_url":"https://github.com/nil123532/learning-to-defer-to-a-population-with-limited-demonstrations","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}