Abstract | ||
---|---|---|
GPT-3 has attracted lots of attention due to its superior performance across a wide range of NLP tasks, especially with its in-context learning abilities. Despite its success, we found that the empirical results of GPT-3 depend heavily on the choice of in-context examples. In this work, we investigate whether there are more effective strategies for judiciously selecting incontext examples (relative to random sampling) that better leverage GPT-3's in-context learning capabilities. Inspired by the recent success of leveraging a retrieval module to augment neural networks, we propose to retrieve examples that are semantically-similar to a test query sample to formulate its corresponding prompt. Intuitively, the examples selected with such a strategy may serve as more informative inputs to unleash GPT-3's power of text generation. We evaluate the proposed approach on several natural language understanding and generation benchmarks, where the retrieval-based prompt selection approach consistently outperforms the random selection baseline. Moreover, it is observed that the sentence encoders fine tuned on task-related datasets yield even more helpful retrieval results. Notably, significant gains are observed on tasks such as table-totext generation (44.3% on the ToTTo dataset) and open-domain question answering (45.5% on the NQ dataset). |
Year | DOI | Venue |
---|---|---|
2022 | 10.18653/v1/2022.deelio-1.10 | PROCEEDINGS OF DEEP LEARNING INSIDE OUT (DEELIO 2022): THE 3RD WORKSHOP ON KNOWLEDGE EXTRACTION AND INTEGRATION FOR DEEP LEARNING ARCHITECTURES |
DocType | Volume | Citations |
Conference | Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiachang Liu | 1 | 0 | 0.34 |
Dinghan Shen | 2 | 108 | 10.37 |
Yizhe Zhang | 3 | 0 | 0.34 |
Bill Dolan | 4 | 2137 | 132.21 |
L. Carin | 5 | 4603 | 339.36 |
Weizhu Chen | 6 | 597 | 38.77 |