Summary of Fine-tuning Vs Prompting, Can Language Models Understand Human Values?, by Pingwei Sun
Fine-tuning vs Prompting, Can Language Models Understand Human Values?
by Pingwei Sun
First submitted to arxiv on: 12 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In a natural language understanding (NLU) challenge, accurately identifying underlying support values in sentences is essential for grasping speaker tendencies. This paper investigates fine-tuning and prompt tuning as potential solutions using the Human Value Detection 2023 dataset. The authors also explore whether pre-trained models can effectively solve this task based on acquired knowledge during the pre-training stage. Additionally, they examine the capabilities of large language models (LLMs) aligned with RLHF in this context. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better understand how speakers tend to express themselves and what kind of values are important to them. The authors tried different techniques to see if it’s possible for computers to learn from these patterns. They used a special dataset called Human Value Detection 2023 and explored the strengths of large language models in this area. |
Keywords
» Artificial intelligence » Fine tuning » Language understanding » Prompt » Rlhf
