提示词交互时:评估分布偏移下用于去混淆的提示词算术
When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift
AI总结:
本研究提出混合提示词算术(HyPA),结合任务提示词与线性化混淆提示词,在多个基准测试中改善分布偏移下的鲁棒性-性能权衡,为提升混淆偏移下的模型鲁棒性提供了参数高效的方法。
摘要:
在分类任务中,模型可能依赖混淆变量来实现强分布内性能,捕获在分布偏移下失效的虚假特征。这种捷径行为会导致分布外场景下性能大幅下降。任务算术通过减去次要模型更新来移除不需要的信号,提供了潜在解决方案,但通常需要全量微调,计算成本高昂。提示调优通过一小组可训练虚拟令牌适配模型,是一种参数高效的替代方案。对生成的提示词进行任务算术,相较于对整个模型进行操作,是一种有吸引力的替代方法,但该方法能在多大程度上限制对虚假特征的依赖仍有待确定。本研究探讨通过任务算术组合软提示词是否能提升对混淆偏移的鲁棒性,提出混合提示词算术(HyPA),将任务提示词与线性化混淆提示词相结合以抵消虚假相关性。在多个基准测试中,HyPA相较于提示词算术基线,在分布偏移下始终改善了鲁棒性-性能权衡。进一步分析HyPA对隐藏表示的影响,发现证据表明其通过减少混淆信号对预测的影响或在表示中抑制混淆信号,从而缓解混淆。这些结果确立了HyPA作为一种参数高效且有前景的方法,可在评估场景下提升混淆偏移下的鲁棒性。
英文摘要:
In classification tasks, models may rely on confounding variables to achieve strong in-distribution performance, capturing spurious features that fail under distribution shift. This shortcut behavior leads to substantial degradation in out-of-distribution settings. Task arithmetic offers a potential solution by removing unwanted signals via subtraction of secondary model updates, but it typically requires full fine-tuning, which is computationally expensive. Prompt tuning provides a parameter-efficient alternative by adapting models through a small set of trainable virtual tokens. Task arithmetic on the resulting prompts presents an appealing alternative to operations on entire models, but the extent to which this approach can limit reliance on spurious features remains to be established. In this work, we study whether composing soft prompts through task arithmetic improves robustness to confounding shifts. We propose Hybrid Prompt Arithmetic (HyPA), which combines task prompts with linearized confounder prompts to counteract spurious correlations. Across multiple benchmarks, HyPA consistently improves the robustness-performance trade-off relative to prompt-arithmetic baselines under distribution shift. We further analyze how HyPA affects hidden representations and find evidence consistent with it mitigating confounding either by reducing the influence of confounder signals on predictions or by suppressing them in the representation. These results establish HyPA as a parameter-efficient and promising approach for improving robustness under confounding shifts in the evaluated setting.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。