mlsanityData to 7 Oct 2026

Gmail Smart Compose: Real-Time Assisted Writing

arXiv 1906.00080 ↗First posted 17 May 2019cs.CL cs.LGcited by 97

Not on the map. Why?

Abstract (arXiv)

In this paper, we present Smart Compose, a novel system for generating interactive, real-time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In the design and deployment of such a large-scale and complicated system, we faced several challenges including model selection, performance evaluation, serving and other practical issues. At the core of Smart Compose is a large-scale neural language model. We leveraged state-of-the-art machine learning techniques for language model training which enabled high-quality suggestion prediction, and constructed novel serving infrastructure for high-throughput and real-time inference. Experimental results show the effectiveness of our proposed system design and deployment approach. This system is currently being served in Gmail.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 16; 2023: 23; 2024: 15; 2025: 10; 2026: 9.

97 papers.

Sort:

By area:

  1. 2022Red Teaming Language Models with Language Modelscited by 983
  2. 2021Membership Inference Attacks From First Principlescited by 839
  3. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 278
  4. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  5. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 194
  6. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  7. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
  8. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 145
  9. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  10. 2022Evaluating Human-Language Model Interactioncited by 90
  11. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 89
  12. 2021A Study of Face Obfuscation in ImageNetcited by 83
38 more
  1. 2021Sparks: Inspiration for Science Writing using Language Modelscited by 80
  2. 2024Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systemscited by 76
  3. 2024A Design Space for Intelligent and Interactive Writing Assistantscited by 76
  4. 2021Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approachcited by 75
  5. 2021The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writerscited by 61
  6. 2024AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuancescited by 59
  7. 2024Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Modelscited by 51
  8. 2022Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summariescited by 47
  9. 2021Zero-Shot Recommender Systemscited by 45
  10. 2021Quantum federated learning through blind quantum computingcited by 44
  11. 2022Memorization in NLP Fine-tuning Methodscited by 43
  12. 2021FRUIT: Faithfully Reflecting Updated Information in Textcited by 39
  13. 2023Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Promptingcited by 36
  14. 2023User Inference Attacks on Large Language Modelscited by 36
  15. 2021Membership Inference on Word Embedding and Beyondcited by 34
  16. 2022Training and Evaluating a Jupyter Notebook Data Science Assistantcited by 31
  17. 2023Privacy Implications of Retrieval-Based Language Modelscited by 31
  18. 2021Fast and Memory Efficient Differentially Private-SGD via JL Projectionscited by 29
  19. 2021Privacy Regularization: Joint Privacy-Utility Optimization in Language Modelscited by 29
  20. 2024Fine-Tuning Large Language Models with User-Level Differential Privacycited by 28
  21. 2022Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writingcited by 27
  22. 2023Helping the Helper: Supporting Peer Counselors via AI-Empowered Practice and Feedbackcited by 23
  23. 2023The AI Ghostwriter Effect: When Users Do Not Perceive Ownership of AI-Generated Text But Self-Declare as Authorscited by 22
  24. 2024GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agencycited by 18
  25. 2022A Blessing of Dimensionality in Membership Inference through Regularizationcited by 17
  26. 2023From Commit Message Generation to History-Aware Commit Message Completioncited by 16
  27. 2025Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Processcited by 14
  28. 2023Next Steps for Human-Centered Generative AI: A Technical Perspectivecited by 13
  29. 2024Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Toolscited by 13
  30. 2021IGA : An Intent-Guided Authoring Assistantcited by 12
  31. 2022Data Isotopes for Data Provenance in DNNscited by 11
  32. 2023CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Modelscited by 10
  33. 2021Spelling Correction with Denoising Transformercited by 9
  34. 2023Comparing Sentence-Level Suggestions to Message-Level Suggestions in AI-Mediated Communicationcited by 9
  35. 2023DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Releasecited by 9
  36. 2021Differentially Private n-gram Extractioncited by 8
  37. 2021Training Data Leakage Analysis in Language Modelscited by 7
  38. 2022Combing for Credentials: Active Pattern Extraction from Smart Replycited by 7

50 most cited of 97 All 97 (JSON)