FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema

arXiv:2402.11811v1 Announce Type: new
Abstract: In the quest to facilitate the deep intelligence of Large Language Models (LLMs) accessible in final-end user-bot interactions, the art of prompt crafting emerges as a critical yet complex task for the average user. Contrast to previous model-oriented yet instruction-agnostic Automatic Prompt Optimization methodologies, yielding polished results for predefined target models while suffering rapid degradation with out-of-box models, we present Free-form Instruction-oriented Prompt Optimization (FIPO). This approach is supported by our large-scale prompt preference dataset …

arxiv cs.cl dataset fine-tuning form free modular optimization prompt schema type