Learning to Select In-Context Demonstration Preferred by Large Language Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916759659872256 |
|---|---|
| author | Zhang, Zheng Lan, Shaocheng Song, Lei Bian, Jiang Li, Yexin Ren, Kan |
| author_facet | Zhang, Zheng Lan, Shaocheng Song, Lei Bian, Jiang Li, Yexin Ren, Kan |
| contents | In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations. However, ICL performance is highly dependent on the selection of these demonstrations. Recent work explores retrieval-based methods for selecting query-specific demonstrations, but these approaches often rely on surrogate objectives such as metric learning, failing to directly optimize ICL performance. Consequently, they struggle to identify truly beneficial demonstrations. Moreover, their discriminative retrieval paradigm is ineffective when the candidate pool lacks sufficient high-quality demonstrations. To address these challenges, we propose GenICL, a novel generative preference learning framework that leverages LLM feedback to directly optimize demonstration selection for ICL. Experiments on 19 datasets across 11 task categories demonstrate that GenICL achieves superior performance than existing methods in selecting the most effective demonstrations, leading to better ICL performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19966 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Select In-Context Demonstration Preferred by Large Language Model Zhang, Zheng Lan, Shaocheng Song, Lei Bian, Jiang Li, Yexin Ren, Kan Machine Learning Artificial Intelligence In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations. However, ICL performance is highly dependent on the selection of these demonstrations. Recent work explores retrieval-based methods for selecting query-specific demonstrations, but these approaches often rely on surrogate objectives such as metric learning, failing to directly optimize ICL performance. Consequently, they struggle to identify truly beneficial demonstrations. Moreover, their discriminative retrieval paradigm is ineffective when the candidate pool lacks sufficient high-quality demonstrations. To address these challenges, we propose GenICL, a novel generative preference learning framework that leverages LLM feedback to directly optimize demonstration selection for ICL. Experiments on 19 datasets across 11 task categories demonstrate that GenICL achieves superior performance than existing methods in selecting the most effective demonstrations, leading to better ICL performance. |
| title | Learning to Select In-Context Demonstration Preferred by Large Language Model |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.19966 |