Prompt and Instruction-Based Tuning for Response Generation in Conversational Question Answering

Yujie Xing, Peng Liu

Abstract: In recent years, prompt-based tuning and instruction-based tuning have emerged as popular approaches for natural language processing. In this paper, we investigate the application of prompt and instruction-based tuning approaches for response generation in conversational question answering. We approach this task from both extractive and generative angles, where we adopt prompt-based tuning for the extractive angle and instruction-based tuning for the generative angle. Additionally, we utilize multi-task learning to integrate these two angles. To evaluate the performance of our proposed approaches, we conduct experiments on the GPT-2 model. The results show that the approaches improve performance by \(18\%\) on F1 score over the baseline. We share our codes and data for reproducibility. (https://github.com/yujie-xing/Multi-Turn_QA_Prompt).