ChatGPT引導的編輯指導員，用於抽象摘要的定制化

摘要

儘管大型語言模型（如ChatGPT）生成質量令人印象深刻，但根據特定用戶需求調整輸出仍然是一個挑戰。在本文中，我們提出了一個三代理生成流程，包括生成器、指導者和編輯器，以增強生成輸出的定制化。生成器產生初始輸出，特定用戶的指導者生成編輯指示，編輯器生成符合用戶偏好的修訂輸出。推理專用的大型語言模型（ChatGPT）既充當生成器又充當編輯器，而較小的模型則充當特定用戶的指導者，引導生成過程以滿足用戶需求。指導者使用編輯器引導的強化學習進行訓練，利用來自大規模編輯器模型的反饋來優化指示生成。在兩個抽象摘要數據集上的實驗結果顯示了我們方法在生成更符合用戶期望的輸出方面的有效性。

English

Tailoring outputs of large language models, such as ChatGPT, to specific user needs remains a challenge despite their impressive generation quality. In this paper, we propose a tri-agent generation pipeline consisting of a generator, an instructor, and an editor to enhance the customization of generated outputs. The generator produces an initial output, the user-specific instructor generates editing instructions, and the editor generates a revised output aligned with user preferences. The inference-only large language model (ChatGPT) serves as both the generator and the editor, while a smaller model acts as the user-specific instructor to guide the generation process toward user needs. The instructor is trained using editor-steered reinforcement learning, leveraging feedback from the large-scale editor model to optimize instruction generation. Experimental results on two abstractive summarization datasets demonstrate the effectiveness of our approach in generating outputs that better fulfill user expectations.

ChatGPT引導的編輯指導員，用於抽象摘要的定制化

ChatGPT-steered Editing Instructor for Customization of Abstractive Summarization

摘要

Support