Advancing Prompt Recovery in NLP: A Deep Dive into the Integration of Gemma-2b-it and Phi2 Models

• Published in: IEEE International Conference on Power, Intelligent Computing and Systems (Online) pp. 934 - 939
• Main Authors: Chen, Jianlong, Xu, Wei, Ding, Zhicheng, Xu, Jinxin, Yan, Hao, Zhang, Xinyu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 26.07.2024
• Subjects: Analytical models; Benchmark testing; Computational modeling; Computer architecture; experimental evaluation; Gemma; Language models; Natural language processing; Phi2 model; pre-trained models; prompt recovery; Technological innovation; Training
• ISSN: 2834-8567
• DOI: 10.1109/ICPICS62053.2024.10796809

Prompt recovery, a crucial task in natural language processing, entails the reconstruction of prompts or instructions that language models use to convert input text into a specific output. Although pivotal, the design and effectiveness of prompts represent a challenging and relatively untapped field within NLP research. This paper delves into an exhaustive investigation of prompt recovery methodologies, employing a spectrum of pre-trained language models and strategies. Our study is a comparative analysis aimed at gauging the efficacy of various models on a benchmark dataset, with the goal of pinpointing the most proficient approach for prompt recovery. Through meticulous experimentation and detailed analysis, we elucidate the outstanding performance of the Gemma-2b-it + Phi2 model + Pretrain. This model surpasses its counterparts, showcasing its exceptional capability in accurately reconstructing prompts for text transformation tasks. Our findings offer a significant contribution to the existing knowledge on prompt recovery, shedding light on the intricacies of prompt design and offering insightful perspectives for future innovations in text rewriting and the broader field of natural language processing.