CoEdIT：透過任務特定指令調整的文本編輯

CoEdIT: Text Editing by Task-Specific Instruction Tuning

May 17, 2023

作者: Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang

cs.AI

摘要

文本編輯或修訂是人類寫作過程中的重要功能。了解大型語言模型（LLMs）在進行高質量修訂和與人類作者合作方面的能力是建立有效寫作助手的關鍵步驟。通過先前LLMs和指示調整的成功，我們利用調整指示的LLMs進行文本修訂，以提高用戶生成文本的質量並改善過程的效率。我們介紹了CoEdIT，這是一個用於寫作輔助的最先進的文本編輯模型。CoEdIT接受用戶提供的指示，指定所需文本的屬性，例如“使句子更簡單”或“以更中性的風格書寫”，並輸出編輯後的文本。我們提出了一個在各種任務特定指示的多樣集合上進行微調的大型語言模型（總共82K個指示）。我們的模型（1）在各種文本編輯基準測試中實現了最先進的性能，（2）與公開可用的在指示上訓練的最大尺寸LLMs相比具有競爭力，同時體積小了約60倍，（3）能夠推廣到未見過的編輯指示，（4）具有組合理解能力，可以推廣到包含不同編輯操作組合的指示。通過廣泛的定性和定量分析，我們展示作者更喜歡CoEdIT建議的編輯，相對於其他最先進的文本編輯模型。我們的代碼和數據集是公開可用的。

English

Text editing or revision is an essential function of the human writing process. Understanding the capabilities of LLMs for making high-quality revisions and collaborating with human writers is a critical step toward building effective writing assistants. With the prior success of LLMs and instruction tuning, we leverage instruction-tuned LLMs for text revision to improve the quality of user-generated text and improve the efficiency of the process. We introduce CoEdIT, a state-of-the-art text editing model 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 sim60x smaller, (3) is capable of generalizing to unseen edit instructions, and (4) exhibits compositional comprehension abilities to generalize to 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 and dataset are publicly available.