# Proofread: Fixes All Errors with One Tap

arXiv: https://arxiv.org/abs/2406.04523 · HTML: https://mlsanity.com/paper/2406.04523/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 30 of 32)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Efficient Content-Based Sparse Attention with Routing Transformers](https://mlsanity.com/paper/2003.05997/) (2020)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://mlsanity.com/paper/2402.14905/) (2024)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [A Recipe For Arbitrary Text Style Transfer with Large Language Models](https://mlsanity.com/paper/2109.03910/) (2021)
- [JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction](https://mlsanity.com/paper/1702.04066/) (2017)
- [ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark](https://mlsanity.com/paper/2303.13648/) (2023)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [An Emulator for Fine-Tuning Large Language Models using Small Language Models](https://mlsanity.com/paper/2310.12962/) (2023)
- [Seq2Edits: Sequence Transduction Using Span-level Edit Operations](https://mlsanity.com/paper/2009.11136/) (2020)
- [Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty](https://mlsanity.com/paper/2308.02019/) (2023)
- [Heuristic-Guided Reinforcement Learning](https://mlsanity.com/paper/2106.02757/) (2021)
- [TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling](https://mlsanity.com/paper/2010.03802/) (2020)
- [Parallel Data Augmentation for Formality Style Transfer](https://mlsanity.com/paper/2005.07522/) (2020)
- [FRUIT: Faithfully Reflecting Updated Information in Text](https://mlsanity.com/paper/2112.08634/) (2021)
- [EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start](https://mlsanity.com/paper/2205.12209/) (2022)
- [Unsupervised Paraphrasing via Deep Reinforcement Learning](https://mlsanity.com/paper/2007.02244/) (2020)
- [Prompting open-source and commercial language models for grammatical error correction of English learner text](https://mlsanity.com/paper/2401.07702/) (2024)
- [Text Generation with Text-Editing Models](https://mlsanity.com/paper/2206.07043/) (2022)

## Built on by (most cited first, 4 of 4)

- [SPHERE: An Evaluation Card for Human-AI Systems](https://mlsanity.com/paper/2504.07971/) (2025)
- [Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications](https://mlsanity.com/paper/2505.18488/) (2025)
- [Rule by Rule: Learning with Confidence through Vocabulary Expansion](https://mlsanity.com/paper/2411.00049/) (2024)
- [WRAVAL -- WRiting Assist eVALuation](https://mlsanity.com/paper/2601.03268/) (2025)

## Abstract (arXiv)

The impressive capabilities in Large Language Models (LLMs) provide a powerful approach to reimagine users' typing experience. This paper demonstrates Proofread, a novel Gboard feature powered by a server-side LLM in Gboard, enabling seamless sentence-level and paragraph-level corrections with a single tap. We describe the complete system in this paper, from data generation, metrics design to model tuning and deployment. To obtain models with sufficient quality, we implement a careful data synthetic pipeline tailored to online use cases, design multifaceted metrics, employ a two-stage tuning approach to acquire the dedicated LLM for the feature: the Supervised Fine Tuning (SFT) for foundational quality, followed by the Reinforcement Learning (RL) tuning approach for targeted refinement. Specifically, we find sequential tuning on Rewrite and proofread tasks yields the best quality in SFT stage, and propose global and direct rewards in the RL tuning stage to seek further improvement. Extensive experiments on a human-labeled golden set showed our tuned PaLM2-XS model achieved 85.56% good ratio. We launched the feature to Pixel 8 devices by serving the model on TPU v5 in Google Cloud, with thousands of daily active users. Serving latency was significantly reduced by quantization, bucket inference, text segmentation, and speculative decoding. Our demo could be seen in hrefhttps://youtu.be/4ZdcuiwFU7IYoutube.