CoEdIT: Text Editing by Task-Specific Instruction Tuning
This provides a more efficient and effective tool for writers needing automated text editing, though it is incremental as it builds on existing instruction-tuning methods.
The paper tackles the problem of text editing for writing assistance by introducing CoEdIT, a fine-tuned large language model that takes task-specific instructions (e.g., 'Make the sentence simpler') and outputs edited text, achieving state-of-the-art performance on benchmarks while being nearly 60x smaller than comparable models.
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 largest-sized LLMs trained on instructions while being nearly 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 state-of-the-art text editing models. Our code, data, and models are publicly available at https://github.com/vipulraheja/coedit.