In-Context Demonstration Selection with Cross Entropy Difference
This addresses the problem of optimizing in-context learning for AI practitioners, but it is incremental as it builds on existing demonstration selection methods.
The paper tackles the challenge of selecting effective in-context demonstrations for large language models in zero-shot tasks by proposing a cross-entropy difference method, which improves performance across various LLMs on a mix-domain dataset of 8 benchmarks.
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.