Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback

TL;DR

This paper introduces Nifty, a method that leverages one-shot implicit negative feedback from user interactions to significantly improve AI-assisted writing accuracy and intent recognition.

Contribution

It proposes a novel approach to incorporate implicit user feedback into AI writing models, enhancing their performance across multiple datasets.

Findings

Up to 34% improvement in Rouge-L score

89% increase in correct intent generation

86% win-rate in human evaluations

Abstract

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.