Fine-tuning vs Prompting, Can Language Models Understand Human Values?
This work addresses the challenge of understanding speaker tendencies in natural language for applications in value-aligned AI, though it appears incremental in comparing established methods.
The paper investigates whether fine-tuning or prompting better enables language models to detect human values in text, using the Human Value Detection 2023 dataset, and finds that fine-tuning yields more accurate results than prompting.
Accurately handling the underlying support values in sentences is crucial for understanding the speaker's tendencies, yet it poses a challenging task in natural language understanding (NLU). In this article, we explore the potential of fine-tuning and prompt tuning in this downstream task, using the Human Value Detection 2023. Additionally, we attempt to validate whether models can effectively solve the problem based on the knowledge acquired during the pre-training stage. Simultaneously, our interest lies in the capabilities of large language models (LLMs) aligned with RLHF in this task, and some preliminary attempts are presented.