# Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision

arXiv: https://arxiv.org/abs/2204.03685 · HTML: https://mlsanity.com/paper/2204.03685/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 12 of 12)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [Understanding Iterative Revision from Human-Written Text](https://mlsanity.com/paper/2203.03802/) (2022)
- [Wordcraft: a Human-AI Collaborative Editor for Story Writing](https://mlsanity.com/paper/2107.07430/) (2021)
- [Learning To Split and Rephrase From Wikipedia Edit History](https://mlsanity.com/paper/1808.09468/) (2018)
- [Text Editing by Command](https://mlsanity.com/paper/2010.12826/) (2020)
- [WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse](https://mlsanity.com/paper/1808.09422/) (2018)
- [Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance](https://mlsanity.com/paper/1910.09180/) (2019)
- [IGA : An Intent-Guided Authoring Assistant](https://mlsanity.com/paper/2104.07000/) (2021)
- [Machine-in-the-Loop Rewriting for Creative Image Captioning](https://mlsanity.com/paper/2111.04193/) (2021)

## Built on by (most cited first, 30 of 46)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing](https://mlsanity.com/paper/2210.13669/) (2022)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison](https://mlsanity.com/paper/2511.07919/) (2025)
- [Beyond the Chat: Executable and Verifiable Text-Editing with LLMs](https://mlsanity.com/paper/2309.15337/) (2023)
- [ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews](https://mlsanity.com/paper/2306.12587/) (2023)
- [Automated Focused Feedback Generation for Scientific Writing Assistance](https://mlsanity.com/paper/2405.20477/) (2024)
- [ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing](https://mlsanity.com/paper/2305.09770/) (2023)
- [Learning to Model Editing Processes](https://mlsanity.com/paper/2205.12374/) (2022)
- [Teaching Language Models to Self-Improve through Interactive Demonstrations](https://mlsanity.com/paper/2310.13522/) (2023)
- [Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters](https://mlsanity.com/paper/2311.11268/) (2023)
- [Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks](https://mlsanity.com/paper/2212.01350/) (2022)
- [GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency](https://mlsanity.com/paper/2402.08855/) (2024)
- [The Future of Continual Learning in the Era of Foundation Models: Three Key Directions](https://mlsanity.com/paper/2506.03320/) (2025)
- [CASIMIR: A Corpus of Scientific Articles enhanced with Multiple Author-Integrated Revisions](https://mlsanity.com/paper/2403.00241/) (2024)
- [Help Me Write a Story: Evaluating LLMs' Ability to Generate Writing Feedback](https://mlsanity.com/paper/2507.16007/) (2025)
- [ScholaWrite: A Dataset of End-to-End Scholarly Writing Process](https://mlsanity.com/paper/2502.02904/) (2025)
- [N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics](https://mlsanity.com/paper/2310.18679/) (2023)
- [From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems](https://mlsanity.com/paper/2503.01424/) (2025)
- [Writing as a testbed for open ended agents](https://mlsanity.com/paper/2503.19711/) (2025)
- [Algorithmic Ghost in the Research Shell: Large Language Models and Academic Knowledge Creation in Management Research](https://mlsanity.com/paper/2303.07304/) (2023)
- [Language Models as Critical Thinking Tools: A Case Study of Philosophers](https://mlsanity.com/paper/2404.04516/) (2024)
- [Identifying Reliable Evaluation Metrics for Scientific Text Revision](https://mlsanity.com/paper/2506.04772/) (2025)
- [Writing Assistants Should Model Social Factors of Language](https://mlsanity.com/paper/2303.16275/) (2023)
- [Text revision in Scientific Writing Assistance: An Overview](https://mlsanity.com/paper/2303.16726/) (2023)
- [generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation](https://mlsanity.com/paper/2403.07627/) (2024)

## Abstract (arXiv)

Revision is an essential part of the human writing process. It tends to be strategic, adaptive, and, more importantly, iterative in nature. Despite the success of large language models on text revision tasks, they are limited to non-iterative, one-shot revisions. Examining and evaluating the capability of large language models for making continuous revisions and collaborating with human writers is a critical step towards building effective writing assistants. In this work, we present a human-in-the-loop iterative text revision system, Read, Revise, Repeat (R3), which aims at achieving high quality text revisions with minimal human efforts by reading model-generated revisions and user feedbacks, revising documents, and repeating human-machine interactions. In R3, a text revision model provides text editing suggestions for human writers, who can accept or reject the suggested edits. The accepted edits are then incorporated into the model for the next iteration of document revision. Writers can therefore revise documents iteratively by interacting with the system and simply accepting/rejecting its suggested edits until the text revision model stops making further revisions or reaches a predefined maximum number of revisions. Empirical experiments show that R3 can generate revisions with comparable acceptance rate to human writers at early revision depths, and the human-machine interaction can get higher quality revisions with fewer iterations and edits. The collected human-model interaction dataset and system code are available at urlhttps://github.com/vipulraheja/IteraTeR. Our system demonstration is available at urlhttps://youtu.be/lK08tIpEoaE.