Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.21868 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909435631239168 |
|---|---|
| author | Mojarradi, M. Mehdi Yang, Lingyi McCraith, Robert Mahdi, Adam |
| author_facet | Mojarradi, M. Mehdi Yang, Lingyi McCraith, Robert Mahdi, Adam |
| contents | Large language models (LLMs) have shown impressive capabilities across various tasks, but their performance on domain-specific tasks remains limited. While methods like retrieval augmented generation and fine-tuning can help to address this, they require significant resources. In-context learning (ICL) is a cheap and efficient alternative but cannot match the accuracies of advanced methods. We present Ensemble SuperICL, a novel approach that enhances ICL by leveraging the expertise of multiple fine-tuned small language models (SLMs). Ensemble SuperICL achieves state of the art (SoTA) results on several natural language understanding benchmarks. Additionally, we test it on a medical-domain labelling task and showcase its practicality by using off-the-shelf SLMs fine-tuned on a general language task, achieving superior accuracy in large-scale data labelling compared to all baselines. Finally, we conduct an ablation study and sensitivity analyses to elucidate the underlying mechanism of Ensemble SuperICL. Our research contributes to the growing demand for efficient domain specialisation methods in LLMs, offering a cheap and effective method for practitioners. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21868 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving In-Context Learning with Small Language Model Ensembles Mojarradi, M. Mehdi Yang, Lingyi McCraith, Robert Mahdi, Adam Computation and Language Large language models (LLMs) have shown impressive capabilities across various tasks, but their performance on domain-specific tasks remains limited. While methods like retrieval augmented generation and fine-tuning can help to address this, they require significant resources. In-context learning (ICL) is a cheap and efficient alternative but cannot match the accuracies of advanced methods. We present Ensemble SuperICL, a novel approach that enhances ICL by leveraging the expertise of multiple fine-tuned small language models (SLMs). Ensemble SuperICL achieves state of the art (SoTA) results on several natural language understanding benchmarks. Additionally, we test it on a medical-domain labelling task and showcase its practicality by using off-the-shelf SLMs fine-tuned on a general language task, achieving superior accuracy in large-scale data labelling compared to all baselines. Finally, we conduct an ablation study and sensitivity analyses to elucidate the underlying mechanism of Ensemble SuperICL. Our research contributes to the growing demand for efficient domain specialisation methods in LLMs, offering a cheap and effective method for practitioners. |
| title | Improving In-Context Learning with Small Language Model Ensembles |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.21868 |