@unpublished{iter2023in-context,
author = {Iter, Dan and Pryzant, Reid and Xu, Ruochen and Wang, Shuohang and Liu, Yang and Zhu, Chenguang},
title = {In-Context Demonstration Selection with Cross Entropy Difference},
year = {2023},
month = {May},
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.},
url = {http://approjects.co.za/?big=en-us/research/publication/in-context-demonstration-selection-with-cross-entropy-difference/},
note = {Arxiv},
}