cs.LG提交于 2026-10-16已译

RDL-Bench: 面向关系数据库的任务感知问答基准

RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases

Yao Cheng · Siqiang Luo

中文摘要

关系数据库（RDB）是企业与科学领域存储结构化数据的主要基础设施。自然语言（NL）接口旨在让用户无需编写 SQL 即可提问，但实际需求常超出 SQL 查询范畴，涉及对当前数据库状态的推理或基于时间约束的历史记录预测。现有基准往往孤立处理这些目标。RDL-Bench 针对真实 RDB 的任务感知问答（QA）填补了这一空白。该基准将问题分为推理导向（答案由当前状态决定）和预测导向（答案依赖时间约束下的未来结果）。每个实例包含 NL 问题、任务元数据、模式信息、时间上下文、可执行证据或目标构建逻辑及指称级真值。RDL-Bench 支持两种评估设置：原生求解器在其预期能力下的表现，以及由路由器将问题分派至相应执行模块的任务感知模块化系统。

关键要点

01现有基准孤立处理数据库推理与预测任务，缺乏统一评估框架。
02提出 RDL-Bench，包含推理导向与预测导向两类任务感知的问答实例。
03实例包含 NL 问题、模式信息、时间上下文及指称级真值等完整元数据。
04支持原生求解器与任务感知模块化系统两种评估设置。

解读

尚无解读。

原始英文摘要

arXiv:2610.21382v1 Announce Type: new Abstract: Relational databases (RDBs) remain the primary infrastructure for storing and managing structured data across enterprise and scientific domains. Natural-language (NL) interfaces to RDBs aim to let users ask questions without writing SQL, but real user needs go beyond SQL-style lookup: some questions require reasoning over the observable database state, while others require predictive inference from historical relational records under temporal constraints. Existing benchmarks address these goals in isolation. To address this gap, we introduce RDL-Bench, a benchmark for task-aware question answering (QA) over real RDBs. RDL-Bench organizes diverse user questions into reasoning-oriented questions, whose answers are determined by the current database state, and prediction-oriented questions, whose answers depend on future outcomes under temporal constraints. Each instance contains an NL question, task metadata, schema information, temporal context, either executable evidence or target-construction logic, and denotation-level ground truth. RDL-Bench supports two evaluation settings: native solvers under their intended capabilities, and task-aware modular systems where a router dispatches each question to an appropriate execution module.