{"ID":2879547,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.16573","arxiv_id":"2508.16573","title":"ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling","abstract":"Dwell time (DT) is a critical post-click metric for evaluating user preference in recommender systems, complementing the traditional click-through rate (CTR). Although multi-task learning is widely adopted to jointly optimize DT and CTR, we observe that multi-task models systematically collapse their DT predictions to the shortest and longest bins, under-predicting the moderate durations. We attribute this moderate-duration bin under-representation to over-reliance on the CTR-DT spurious correlation, and propose ORCA to address it with causal-decoupling. Specifically, ORCA explicitly models and subtracts CTR's negative transfer while preserving its positive transfer. We further introduce (i) feature-level counterfactual intervention, and (ii) a task-interaction module with instance inverse-weighting, weakening CTR-mediated effect and restoring direct DT semantics. ORCA is model-agnostic and easy to deploy. Experiments show an average 10.6% lift in DT metrics without harming CTR. Code is available at https://github.com/Chrissie-Law/ORCA-Mitigating-Over-Reliance-for-Multi-Task-Dwell-Time-Prediction-with-Causal-Decoupling.","short_abstract":"Dwell time (DT) is a critical post-click metric for evaluating user preference in recommender systems, complementing the traditional click-through rate (CTR). Although multi-task learning is widely adopted to jointly optimize DT and CTR, we observe that multi-task models systematically collapse their DT predictions to...","url_abs":"https://arxiv.org/abs/2508.16573","url_pdf":"https://arxiv.org/pdf/2508.16573v1","authors":"[\"Huishi Luo\",\"Fuzhen Zhuang\",\"Yongchun Zhu\",\"Yiqing Wu\",\"Bo Kang\",\"Ruobing Xie\",\"Feng Xia\",\"Deqing Wang\",\"Jin Dong\"]","published":"2025-08-22T17:56:01Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false,"code_links":[{"ID":610593,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2879547,"paper_url":"https://arxiv.org/abs/2508.16573","paper_title":"ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling","repo_url":"https://github.com/Chrissie-Law/ORCA-Mitigating-Over-Reliance-for-Multi-Task-Dwell-Time-Prediction-with-Causal-Decoupling","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}