# Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback

arXiv: https://arxiv.org/abs/2410.11009 · HTML: https://mlsanity.com/paper/2410.11009/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Efficient Natural Language Response Suggestion for Smart Reply](https://mlsanity.com/paper/1705.00652/) (2017)
- [Gmail Smart Compose: Real-Time Assisted Writing](https://mlsanity.com/paper/1906.00080/) (2019)
- [Rewarding Chatbots for Real-World Engagement with Millions of Users](https://mlsanity.com/paper/2303.06135/) (2023)
- [Smart Reply: Automated Response Suggestion for Email](https://mlsanity.com/paper/1606.04870/) (2016)
- [DIRECTOR: Generator-Classifiers For Supervised Language Modeling](https://mlsanity.com/paper/2206.07694/) (2022)
- [Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity](https://mlsanity.com/paper/2112.05843/) (2021)
- [Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance](https://mlsanity.com/paper/1910.09180/) (2019)
- [Diversifying Reply Suggestions using a Matching-Conditional Variational Autoencoder](https://mlsanity.com/paper/1903.10630/) (2019)
- [IGA : An Intent-Guided Authoring Assistant](https://mlsanity.com/paper/2104.07000/) (2021)
- [A Dataset and Baselines for Multilingual Reply Suggestion](https://mlsanity.com/paper/2106.02017/) (2021)
- [Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation](https://mlsanity.com/paper/2205.06058/) (2022)
- [OCC: A Smart Reply System for Efficient In-App Communications](https://mlsanity.com/paper/1907.08167/) (2019)
- [Who Wrote this? How Smart Replies Impact Language and Agency in the Workplace](https://mlsanity.com/paper/2210.06470/) (2022)
- [Smart Word Suggestions for Writing Assistance](https://mlsanity.com/paper/2305.09975/) (2023)
- [Learning and Optimization of Implicit Negative Feedback for Industrial Short-video Recommender System](https://mlsanity.com/paper/2308.13249/) (2023)
- [End-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems](https://mlsanity.com/paper/2310.18956/) (2023)

## Abstract (arXiv)

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.