In-Context Example Ordering Guided by Label Distributions
CoRR(2024)
摘要
By allowing models to predict without task-specific training, in-context
learning (ICL) with pretrained LLMs has enormous potential in NLP. However, a
number of problems persist in ICL. In particular, its performance is sensitive
to the choice and order of in-context examples. Given the same set of
in-context examples with different orderings, model performance may vary
between near random to near state-of-the-art. In this work, we formulate
in-context example ordering as an optimization problem. We examine three
problem settings that differ in the assumptions they make about what is known
about the task. Inspired by the idea of learning from label proportions, we
propose two principles for in-context example ordering guided by model's
probability predictions. We apply our proposed principles to thirteen text
classification datasets and nine different autoregressive LLMs with 700M to 13B
parameters. We demonstrate that our approach outperforms the baselines by
improving the classification accuracy, reducing model miscalibration, and also
by selecting better in-context examples.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要