Paper · arXiv 2305.02483
ChatGPT-steered Editing Instructor for Customization of Abstractive Summarization
Wen Xiao, Yujia Xie, Giuseppe Carenini, Pengcheng He
A tri-agent pipeline for enhancing customizability of large language model outputs includes a generator, an instructor, and an editor, with the instructor being optimized through reinforcement learning guided by the editor.
Abstract
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.