cs.AI updates on arXiv.org 07月09日 12:01
Mitigating Shortcut Learning with InterpoLated Learning
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出了一种名为InterpoLL的新方法,通过插值学习来弱化模型中 shortcuts 的影响,从而提高模型在少数样本上的泛化能力,同时在不降低多数样本准确率的情况下,展示了其在多种自然语言理解任务上的有效性。

arXiv:2507.05527v1 Announce Type: cross Abstract: Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This reliance hinders generalization on minority examples, where such correlations do not hold. Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. To address these issues, we propose InterpoLated Learning (InterpoLL) which interpolates the representations of majority examples to include features from intra-class minority examples with shortcut-mitigating patterns. This weakens shortcut influence, enabling models to acquire features predictive across both minority and majority examples. Experimental results on multiple natural language understanding tasks demonstrate that InterpoLL improves minority generalization over both ERM and state-of-the-art shortcut mitigation methods, without compromising accuracy on majority examples. Notably, these gains persist across encoder, encoder-decoder, and decoder-only architectures, demonstrating the method's broad applicability.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

InterpoLL 模型泛化 少数样本 自然语言理解
相关文章