Abstract
There has been a growing body of work focusing on the in-context learning (ICL) abilities of large language models (LLMs). However, it is an open question how effective ICL can be. This paper presents Tutor-ICL, a simple prompting method for classification tasks inspired by how effective instructors might engage their students in learning a task. Specifically, we propose presenting exemplar answers in a *comparative format* rather than the traditional single-answer format. We also show that including the test instance before the exemplars can improve performance, making it easier for LLMs to focus on relevant exemplars. Lastly, we include a summarization step before attempting the test, following a common human practice. Experiments on various classification tasks, conducted across both decoder-only LLMs (Llama 2, 3) and encoder-decoder LLMs (Flan-T5-XL, XXL), show that Tutor-ICL consistently boosts performance, achieving up to a 13.76% increase in accuracy.- Anthology ID:
- 2024.findings-emnlp.554
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9496–9506
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2024.findings-emnlp.554/
- DOI:
- 10.18653/v1/2024.findings-emnlp.554
- Cite (ACL):
- Ikhyun Cho, Gaeul Kwon, and Julia Hockenmaier. 2024. Tutor-ICL: Guiding Large Language Models for Improved In-Context Learning Performance. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9496–9506, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Tutor-ICL: Guiding Large Language Models for Improved In-Context Learning Performance (Cho et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2024.findings-emnlp.554.pdf