论文标题
部分可观测时空混沌系统的无模型预测
Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback
论文作者
论文摘要
为了进行摘要，人类的偏好对摘要者的驯服产量至关重要，而对人类的利益至关重要，因为地面摘要稀缺和模棱两可。实际设置需要在人与人工智能代理之间进行动态交流，其中以在线方式提供反馈。在本文中，我们介绍了一个新框架，以交互方式培训具有首选项反馈的摘要模型。通过正确利用离线数据和新颖的奖励模型，我们可以提高有关胭脂分数和样本效率的性能。我们在三个不同数据集上的实验证实了拟议框架在优先学习的主动，很少和在线设置中的好处。
For summarization, human preference is critical to tame outputs of the summarizer in favor of human interests, as ground-truth summaries are scarce and ambiguous. Practical settings require dynamic exchanges between human and AI agent wherein feedback is provided in an online manner, a few at a time. In this paper, we introduce a new framework to train summarization models with preference feedback interactively. By properly leveraging offline data and a novel reward model, we improve the performance regarding ROUGE scores and sample-efficiency. Our experiments on three various datasets confirm the benefit of the proposed framework in active, few-shot and online settings of preference learning.
