EdgeLM：面向语言模型表格理解的边缘演示

中文摘要 AI 辅助

大型语言模型（LLMs）通过上下文学习完成以表格为中心的预测，因此演示选择对性能至关重要。现有检索方法优先考虑与查询的相似度，但相似演示往往会强化模型的可能预测，而非揭示困难决策所需的差异。我们提出EdgeLM，一种检索框架，它转而选择边缘证据，即既与查询相关又对决策边界有信息量的演示。EdgeLM通过选择数据边缘（具有不同真实标签的邻近示例）和模型边缘（已部署模型之前误分类的相似示例）两种互补形式的边缘证据进行检索。EdgeLM既不需要模型重新训练，也不需要特定任务的工程设计。在五个数据整理任务、十五个数据集以及五个开放权重和专有LLMs上，EdgeLM在每种设置中始终取得最佳或接近最佳的性能，而 ablation 实验表明，两种形式的边缘证据提供了互补的益处。我们的代码和数据集可在此https URL公开获取。

英文摘要

Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Existing retrieval methods prioritize similarity to the query, but similar demonstrations often reinforce the model's likely prediction rather than reveal the distinctions needed for difficult decisions. We propose EdgeLM, a retrieval framework that instead selects edge evidence, demonstrations that are both relevant to the query and informative about the decision boundary. EdgeLM retrieves two complementary forms of edge evidence by selecting data edges, nearby examples with different ground-truth labels, and model edges, similar examples previously misclassified by the deployed model. EdgeLM requires neither model retraining nor task-specific engineering. Across five data wrangling tasks, fifteen datasets, and five open-weight and proprietary LLMs, EdgeLM consistently achieves the best or near-best performance in every setting, while ablations show that the two forms of edge evidence provide complementary benefits. Our code and datasets are publicly available at https://github.com/soroushomidvar/EdgeLM.

发表机构

• University of Alberta（阿尔伯塔大学）

机构由 AI 辅助整理，请以论文原文为准。