发表机构
University of Texas at Arlington（德克萨斯大学阿灵顿分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
STEER通过利用大型语言模型对数据库模式外键进行相关性排序，将推理上下文集中在最相关的表上，平均减少约40%的上下文大小，同时保持或提升预测准确性。
AI 中文摘要
关系基础模型（RFMs）在包含多个关系数据库和预测任务的集合上进行一次预训练，然后以零样本方式应用于之前未见过的数据库和任务。为了对目标行进行预测，RFM会采样与该行通过外键连接的行邻域，并将该邻域作为其推理上下文。降低推理成本是任何基础模型的重要目标，对于RFM而言，该成本随上下文大小的增加而增长。缩小上下文的最简单方法是丢弃部分采样行，但这忽略了数据库模式的语义，因此丢弃信息行与非信息行的可能性相当。我们提出STEER，一种采样方法，通过将推理上下文集中在与当前预测任务最相关的表上来缩小上下文。STEER通过提示大型语言模型将数据库模式的外键边按相关性层级排序，以获取相关性信息，然后将每个层级映射为在遍历过程中遵循该边的概率。由于排序仅使用模式，因此每个任务仅计算一次，并在所有后续预测中重用，从而摊销其成本。我们在三种最先进的RFM（RT、RT-J和Griffin）上评估了STEER，结果表明，它平均将推理上下文大小减少了约40%，同时保持甚至在某些情况下提高了预测准确性。
英文摘要
Relational foundation models (RFMs) are pretrained once on a collection of relational databases and prediction tasks, and then applied zero-shot to previously unseen databases and tasks. To make a prediction for a target row, an RFM samples a neighborhood of rows linked to that row through foreign keys and uses this neighborhood as its inference context. Lowering inference cost is an important goal for any foundation model, and for RFMs this cost grows with the size of the context. The simplest ways to shrink the context is to drop some of the sampled rows, but this ignores the semantics of the database schema, so it is as likely to discard informative rows as uninformative ones. We propose STEER, a sampling approach that shrinks the inference context by concentrating it on the tables most relevant to the prediction task at hand. STEER obtains relevance information by prompting a large language model to rank the foreign-key edges of the database schema into relevance tiers for the given task, and then maps each tier to a probability of following that edge during traversal. Because the ranking uses only the schema, it is computed once per task and reused across all subsequent predictions, amortizing its cost. We evaluate STEER on three state-of-the-art RFMs (RT, RT-J, and Griffin) and show that it reduces inference context size by about 40% on average while maintaining, and in some cases improving, prediction accuracy.
