Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.14673 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917782229090304 |
|---|---|
| author | Wang, Taihang Xu, Xiaoman Wang, Yimin Jiang, Ye |
| author_facet | Wang, Taihang Xu, Xiaoman Wang, Yimin Jiang, Ye |
| contents | Real-world applications of large language models (LLMs) in computational social science (CSS) tasks primarily depend on the effectiveness of instruction tuning (IT) or in-context learning (ICL). While IT has shown highly effective at fine-tuning LLMs for various tasks, ICL offers a rapid alternative for task adaptation by learning from examples without explicit gradient updates. In this paper, we evaluate the classification performance of LLMs using IT versus ICL in few-shot CSS tasks. The experimental results indicate that ICL consistently outperforms IT in most CSS tasks. Additionally, we investigate the relationship between the increasing number of training samples and LLM performance. Our findings show that simply increasing the number of samples without considering their quality does not consistently enhance the performance of LLMs with either ICL or IT and can sometimes even result in a performance decline. Finally, we compare three prompting strategies, demonstrating that ICL is more effective than zero-shot and Chain-of-Thought (CoT). Our research highlights the significant advantages of ICL in handling CSS tasks in few-shot settings and emphasizes the importance of optimizing sample quality and prompting strategies to improve LLM classification performance. The code will be made available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14673 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science Wang, Taihang Xu, Xiaoman Wang, Yimin Jiang, Ye Computation and Language Artificial Intelligence Real-world applications of large language models (LLMs) in computational social science (CSS) tasks primarily depend on the effectiveness of instruction tuning (IT) or in-context learning (ICL). While IT has shown highly effective at fine-tuning LLMs for various tasks, ICL offers a rapid alternative for task adaptation by learning from examples without explicit gradient updates. In this paper, we evaluate the classification performance of LLMs using IT versus ICL in few-shot CSS tasks. The experimental results indicate that ICL consistently outperforms IT in most CSS tasks. Additionally, we investigate the relationship between the increasing number of training samples and LLM performance. Our findings show that simply increasing the number of samples without considering their quality does not consistently enhance the performance of LLMs with either ICL or IT and can sometimes even result in a performance decline. Finally, we compare three prompting strategies, demonstrating that ICL is more effective than zero-shot and Chain-of-Thought (CoT). Our research highlights the significant advantages of ICL in handling CSS tasks in few-shot settings and emphasizes the importance of optimizing sample quality and prompting strategies to improve LLM classification performance. The code will be made available. |
| title | Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2409.14673 |