用用户不选回复的隐式反馈，提升AI写作准确率
Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback
- 通过分类器引导，将用户不选回复作为负反馈融入生成过程
- 在多任务对话数据集上，召回率提升34%，意图正确率达89%
- 适合想用用户行为优化AI写作的工程师和产品经理
AI辅助沟通可提升交流效率，已有智能回复与AI写作系统。但输入形式与架构差异大，难以跨系统共享用户行为洞察。本文研究用户未选择智能回复这一行为，将其作为单次隐式负反馈，用于提升AI写作模型准确性。提出Nifty方法，利用分类器引导实现对隐式反馈的可控融合。实验表明，在MultiWOZ和Schema-Guided Dialog数据集上，相比基线系统，Rouge-L提升达34%，意图生成正确率提高89%，人类评估胜率高达86%。
原文摘要 · Abstract (English)
AI-mediated communication enables users to communicate more quickly and efficiently. Various systems have been proposed such as smart reply and AI-assisted writing. Yet, the heterogeneity of the forms of inputs and architectures often renders it challenging to combine insights from user behaviour in one system to improve performance in another. In this work, we consider the case where the user does not select any of the suggested replies from a smart reply system, and how this can be used as one-shot implicit negative feedback to enhance the accuracy of an AI writing model. We introduce Nifty, an approach that uses classifier guidance to controllably integrate implicit user feedback into the text generation process. Empirically, we find up to 34% improvement in Rouge-L, 89% improvement in generating the correct intent, and an 86% win-rate according to human evaluators compared to a vanilla AI writing system on the MultiWOZ and Schema-Guided Dialog datasets.
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。