# Learning to Model Editing Processes

arXiv: https://arxiv.org/abs/2205.12374 · HTML: https://mlsanity.com/paper/2205.12374/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Adaptive Input Representations for Neural Language Modeling](https://mlsanity.com/paper/1809.10853/) (2018)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement](https://mlsanity.com/paper/1802.06901/) (2018)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling](https://mlsanity.com/paper/1811.10996/) (2018)
- [Felix: Flexible Text Editing Through Tagging and Insertion](https://mlsanity.com/paper/2003.10687/) (2020)
- [Understanding Iterative Revision from Human-Written Text](https://mlsanity.com/paper/2203.03802/) (2022)
- [Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision](https://mlsanity.com/paper/2204.03685/) (2022)
- [LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2105.08206/) (2021)
- [Unsupervised Text Generation by Learning from Search](https://mlsanity.com/paper/2007.08557/) (2020)
- [Learning to Represent Edits](https://mlsanity.com/paper/1810.13337/) (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)
- [A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes](https://mlsanity.com/paper/1704.04856/) (2017)
- [Learning Structural Edits via Incremental Tree Transformations](https://mlsanity.com/paper/2101.12087/) (2021)
- [Variational Inference for Learning Representations of Natural Language Edits](https://mlsanity.com/paper/2004.09143/) (2020)
- [An Edit-centric Approach for Wikipedia Article Quality Assessment](https://mlsanity.com/paper/1909.08880/) (2019)
- [Text Morphing](https://mlsanity.com/paper/1810.00341/) (2018)

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

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs](https://mlsanity.com/paper/2305.08844/) (2023)
- [DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback](https://mlsanity.com/paper/2311.10081/) (2023)
- [Aligner: Efficient Alignment by Learning to Correct](https://mlsanity.com/paper/2402.02416/) (2024)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation](https://mlsanity.com/paper/2305.00955/) (2023)
- [SummIt: Iterative Text Summarization via ChatGPT](https://mlsanity.com/paper/2305.14835/) (2023)
- [Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits](https://mlsanity.com/paper/2409.14509/) (2024)
- [DiffusER: Discrete Diffusion via Edit-based Reconstruction](https://mlsanity.com/paper/2210.16886/) (2022)
- [ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews](https://mlsanity.com/paper/2306.12587/) (2023)
- [Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits](https://mlsanity.com/paper/2301.00355/) (2023)
- [Flows: Building Blocks of Reasoning and Collaborating AI](https://mlsanity.com/paper/2308.01285/) (2023)
- [Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language](https://mlsanity.com/paper/2311.14543/) (2023)
- [The Better Angels of Machine Personality: How Personality Relates to LLM Safety](https://mlsanity.com/paper/2407.12344/) (2024)
- [GrACE: Generation using Associated Code Edits](https://mlsanity.com/paper/2305.14129/) (2023)
- [Artificial Intelligence for Operations Research: Revolutionizing the Operations Research Process](https://mlsanity.com/paper/2401.03244/) (2024)
- [Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing](https://mlsanity.com/paper/2305.18584/) (2023)
- [Non-autoregressive Text Editing with Copy-aware Latent Alignments](https://mlsanity.com/paper/2310.07821/) (2023)
- [Grounding Natural Language to SQL Translation with Data-Based Self-Explanations](https://mlsanity.com/paper/2411.02948/) (2024)
- [XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates](https://mlsanity.com/paper/2309.11063/) (2023)
- [Automatic and Human-AI Interactive Text Generation](https://mlsanity.com/paper/2310.03878/) (2023)
- [DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism](https://mlsanity.com/paper/2311.14920/) (2023)
- [Learning Extrapolative Sequence Transformations from Markov Chains](https://mlsanity.com/paper/2505.20251/) (2025)
- [EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification](https://mlsanity.com/paper/2606.07915/) (2026)

## Abstract (arXiv)

Most existing sequence generation models produce outputs in one pass, usually left-to-right. However, this is in contrast with a more natural approach that humans use in generating content; iterative refinement and editing. Recent work has introduced edit-based models for various tasks (such as neural machine translation and text style transfer), but these generally model a single edit step. In this work, we propose modeling editing processes, modeling the whole process of iteratively generating sequences. We form a conceptual framework to describe the likelihood of multi-step edits, and describe neural models that can learn a generative model of sequences based on these multistep edits. We introduce baseline results and metrics on this task, finding that modeling editing processes improves performance on a variety of axes on both our proposed task and related downstream tasks compared to previous single-step models of edits.