[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

In-Context Demonstration Selection with Cross Entropy Difference

Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu


Abstract
Large language models (LLMs) can use in-context demonstrations to improve performance on zero-shot tasks. However, selecting the best in-context examples is challenging because model performance can vary widely depending on the selected examples. We present a cross-entropy difference (CED) method for selecting in-context demonstrations. Our method is based on the observation that the effectiveness of in-context demonstrations negatively correlates with the perplexity of the test example by a language model that was finetuned on that demonstration. We utilize parameter efficient finetuning to train small models on training data that are used for computing the cross-entropy difference between a test example and every candidate in-context demonstration. This metric is used to rank and select in-context demonstrations independently for each test input. We evaluate our method on a mix-domain dataset that combines 8 benchmarks, representing 4 text generation tasks, showing that CED for in-context demonstration selection can improve performance for a variety of LLMs over baseline selection methods.
Anthology ID:
2023.findings-emnlp.81
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1150–1162
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.81
DOI:
10.18653/v1/2023.findings-emnlp.81
Bibkey:
Cite (ACL):
Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, and Chenguang Zhu. 2023. In-Context Demonstration Selection with Cross Entropy Difference. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1150–1162, Singapore. Association for Computational Linguistics.
Cite (Informal):
In-Context Demonstration Selection with Cross Entropy Difference (Iter et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.81.pdf