Lune

EMNLP Findings2023

CoEdIT: Text Editing by Task-Specific Instruction Tuning

Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang

Abstract

We introduce COEDIT, a state-of-the-art text editing system for writing assistance.COEDIT takes instructions from the user specifying the attributes of the desired text, such as "Make the sentence simpler" or "Write it in a more neutral style," and outputs the edited text.We present a large language model fine-tuned on a diverse collection of task-specific instructions for text editing (a total of 82K instructions).Our model (1) achieves state-of-the-art performance on various text editing benchmarks, (2) is competitive with publicly available largestsized LLMs trained on instructions while being ∼60x smaller, (3) is capable of generalizing to unseen edit instructions, and (4) exhibits abilities to generalize to composite instructions containing different combinations of edit actions.Through extensive qualitative and quantitative analysis, we show that writers prefer the edits suggested by COEDIT, relative to other stateof-the-art text editing models 1 .Edit Intention / Task Verbalizers GEC Fix grammar, Fix grammar in this sentence, Fix grammar in the sentence, Fix grammar errors, Fix grammatical errors, Fix grammaticality, Fix all grammatical errors, Fix grammatical errors in this sentence, Fix grammar errors in this sentence, Fix grammatical mistakes in this sentence, Fix grammaticality in this sentence, Fix grammaticality of the sentence, Fix disfluencies in the sentence, Make the sentence grammatical, Make the sentence fluent, Fix errors in this text, Update to remove grammar errors, Remove all grammatical errors from this text, Improve the grammar of this text, Improve the grammaticality, Improve the grammaticality of this text, Improve the grammaticality of this sentence, Grammar improvements, Remove grammar mistakes, Remove grammatical mistakes, Fix the grammar mistakes, Fix grammatical mistakes Clarity Clarify the sentence, Clarify this sentence, Clarify this text, Write a clearer version for the sentence, Write a clarified version of the sentence, Write a readable version of the sentence, Write a better readable version of the sentence, Rewrite the sentence more clearly, Rewrite this sentence clearly, Rewrite this sentence for clarity, Rewrite this sentence for readability, Improve this sentence for readability, Make this sentence better readable, Make this sentence more readable, Make this sentence readable, Make the sentence clear, Make the sentence clearer, Clarify, Make the text more understandable, Make this easier to read, Clarification, Change to clearer wording, Clarify this paragraph, Use clearer wording Simplification Simplify the sentence, Simplify this sentence, Simplify this text, Write a simpler version for the sentence, Rewrite the sentence to be simpler, Rewrite this sentence in a simpler manner, Rewrite this sentence for simplicity, Rewrite this with simpler wording, Make the sentence simple, Make the sentence simpler, Make this text less complex, Make this simpler, Simplify, Simplification, Change to simpler wording, Simplify this paragraph, Simplify this text, Use simpler wording, Make this easier to understand Coherence Fix coherence, Fix coherence in this sentence, Fix coherence in the sentence, Fix coherence in this text, Fix coherence in the text, Fix coherence errors, Fix sentence flow, Fix sentence transition, Fix coherence errors in this sentence, Fix coherence mistakes in this sentence, Fix coherence in this sentence, Fix coherence of the sentence, Fix lack of coherence in the sentence, Make the text more coherent, Make the text coherent, Make the text more cohesive, logically linked and consistent as a whole, Make the text more cohesive, Improve the cohesiveness of the text, Make the text more logical, Make the text more consistent, Improve the consistency of the text, Make the text clearer, Improve the coherence of the text Formality Style Transfer Formalize, Improve formality, Formalize the sentence, Formalize this sentence, Formalize the text, Formalize this text, Make this formal, Make this more formal, Make this sound more formal, Make the sentence formal, Make the sentence more formal, Make the sentence sound more formal, Write more formally, Write less informally, Rewrite more formally, Write this more formally, Rewrite this more formally, Write in a formal manner, Write in a more formal manner, Rewrite in a more formal manner Neutralization Remove POV, Remove POVs, Remove POV in this text, Remove POVs in this text, Neutralize this text, Neutralize the text, Neutralize this sentence, Neutralize the sentence, Make this more neutral, Make this text more neutral, Make this sentence more neutral, Make this paragraph more neutral, Remove unsourced opinions, Remove unsourced opinions from this text, Remove non-neutral POVs, Remove non-neutral POV, Remove non-neutral points of view, Remove points of view, Make this text less biased

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

16 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Multitask Prompted Training Enables Zero-Shot Task Generalization cites Finetuned Language Models are Zero-Shot Learners
  • Finetuned Language Models are Zero-Shot Learners cites Multitask Prompted Training Enables Zero-Shot Task Generalization
  • The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites Multitask Prompted Training Enables Zero-Shot Task Generalization
  • The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites Finetuned Language Models are Zero-Shot Learners
  • The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
  • Explainable Notes: Examining How to Unlock Meaning in Medical Notes with Interactivity and Artificial Intelligence cites Beyond the Chat: Executable and Verifiable Text-Editing with LLMs
  • Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning cites Multitask Prompted Training Enables Zero-Shot Task Generalization
  • Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning cites Finetuned Language Models are Zero-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers16

  1. A Design Space for Intelligent and Interactive Writing AssistantsMina Lee, Katy Ilonka Gero, John Joon Young Chung, Simon Buckingham Shum et al.CHI 2024 · 133 citations
  2. ALP: Adaptive Lossless floating-Point CompressionAzim Afroozeh, Leonardo Kuffó, Peter BonczSIGMOD 2024 · 33 citations
  3. Beyond the Chat: Executable and Verifiable Text-Editing with LLMsPhilippe Laban, Jesse Vig, Marti A. Hearst, Caiming Xiong et al.UIST 2024 · 29 citations
  4. Sustaining Human Agency, Attending to Its Cost: An Investigation into Generative AI Design for Non-Native Speakers' Language UseYimin Xiao, Cartor Hancock, Sweta Agrawal, Nikita Mehandru et al.CHI 2025 · 18 citations
  5. Explainable Notes: Examining How to Unlock Meaning in Medical Notes with Interactivity and Artificial IntelligenceHita Kambhamettu, Danaë Metaxa, Kevin Johnson, Andrew HeadCHI 2024 · 16 citations

Builds on17

  1. Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
  2. Multitask Prompted Training Enables Zero-Shot Task GeneralizationVictor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach et al.ICLR 2022 · 1,976 citations
  3. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order SensitivityYao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel et al.ACL 2022 · 1,494 citations
  4. Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context LearningHaokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta et al.NeurIPS 2022 · 1,483 citations
  5. The Flan Collection: Designing Data and Methods for Effective Instruction TuningShayne Longpre, Le Hou, Tu Vu, Albert Webson et al.ICML 2023 · 908 citations

Related papers

  1. Improving Iterative Text Revision by Learning Where to Edit from Other Revision TasksZae Myung Kim, Wanyu Du, Vipul Raheja, Dhruv Kumar et al.EMNLP 2022 · 8 citations
  2. Reducing Sequence Length by Predicting Edit Spans with Large Language ModelsMasahiro Kaneko, Naoaki OkazakiEMNLP 2023 · 3 citations
  3. Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text ModificationsYiming Zeng, Wanhao Yu, Zexin Li, Tao Ren et al.EMNLP Findings 2025 · 12 citations
  4. CoditT5: Pretraining for Source Code and Natural Language EditingJiyang Zhang, Sheena Panthaplackel, Pengyu Nie, Junyi Jessy Li et al.ASE 2022 · 81 citations
  5. Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented ApproachJingyuan Yang, Dapeng Chen, Yajing Sun, Rongjun Li et al.ACL Findings 2024 · 7 citations
Dusk over the sea between two cliffs drawn in fine vertical lines