2022/03/24 by Jinghui Lu, Lu, Jinghui, Linyi Yang +5 · 1 citation
Computer Science · Medicine · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #cs.AI #cs.CL #cs.HC
paper · pdf · doi:10.48550/arxiv.2203.12918
Accepted to ACL 2022
arxiv created 2022/03/24 · openalex publication_date 2022/03/24 · arxiv updated 2022/03/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual generation and dynamic human-intervened correction, RDL exploits rationales (i.e. phrases that cause the prediction), human interventions and semi-factual augmentations to decouple spurious associations and bias models towards generally applicable underlying distributions, which enables fast and accurate generalisation. Experimental results show that RDL leads to significant prediction benefits on both in-distribution and out-of-distribution tests compared to many state-of-the-art benchmarks -- especially for few-shot learning scenarios. We also perform extensive ablation studies to support in-depth analyses of each component in our framework.