提出多阶段框架，让人类与AI协作更高效省钱。
PLACO: A Multi-Stage Framework for Cost-Effective Performance in Human-AI Teams
- 分阶段融合人类与AI判断，动态优化决策流程。
- 在分类任务中实现比单独使用人或模型更高准确率。
- 适合需要低成本高效率的人机协作场景。
人类与AI团队在双方单独无法达成目标时，能显著提升系统性能。随着生成式AI的普及，从写作文到开发算法等日常任务已演变为人类与AI协同完成的任务。在最终输出为单一硬标签的分类任务中，如何融合人类与模型的输出至关重要。先前工作通过贝叶斯规则解决此问题，假设在真实标签条件下，人类与模型输出相互独立。具体方法是结合一个确定性标签者（人类）和一个概率性标签者（分类模型），利用模型的实例级概率与人类的类别级校准概率进行融合。
原文摘要 · Abstract (English)
Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their own. With the advent of powerful and accessible Generative AI models, several mundane tasks have morphed into Human-AI team tasks. From writing essays to developing advanced algorithms, humans have found that using AI assistance has led to an accelerated work pace like never before. In classification tasks, where the final output is a single hard label, it is crucial to address the combination of human and model output. Prior work elegantly solves this problem using Bayes rule, using the assumption that human and model output are conditionally independent given the ground truth. Specifically, it discusses a combination method to combine a single deterministic labeler (the human) and a probabilistic labeler (the classifier model) using the model's instance-level and the human's class-level calibrated probabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。