提出新评估指标ROSE，更准确衡量NL2SQL模型是否真正理解用户意图。
ROSE: An Intent-Centered Evaluation Metric for NL2SQL
- 用对抗式验证-反驳机制判断预测SQL是否符合用户意图。
- 在专家标注数据集上与人工判断一致性超现有指标24%（Kappa值）。
- 适合追求真实语义理解能力的NL2SQL研究者使用。
执行准确率（EX）作为自然语言转SQL（NL2SQL）评估的主流指标，正变得不可靠：它对语法变化敏感，忽略问题可能有多种解释，且易受错误真值SQL误导。为此，我们提出ROSE——一种以意图为中心的评估指标，关注预测的SQL是否回答了用户问题，而非与参考真值的语法一致。ROSE采用对抗式验证-反驳级联结构：验证器独立评估预测SQL的语义正确性，反驳者则以真值SQL为证据挑战并修正该判断。在专家对齐的验证集ROSE-VEC上，ROSE与人类专家的一致性最佳，比次优指标高出近24%的科恩κ系数。我们还对19个NL2SQL方法进行了大规模重评估，揭示四项重要发现。ROSE与ROSE-VEC已开源，以促进更可靠的NL2SQL研究。
原文摘要 · Abstract (English)
Execution Accuracy (EX), the widely used metric for evaluating the effectiveness of Natural Language to SQL (NL2SQL) solutions, is becoming increasingly unreliable. It is sensitive to syntactic variation, ignores that questions may admit multiple interpretations, and is easily misled by erroneous ground-truth SQL. To address this, we introduce ROSE, an intent-centered metric that focuses on whether the predicted SQL answers the question, rather than consistency with the ground-truth SQL under the reference-dependent paradigm. ROSE employs an adversarial Prover-Refuter cascade: SQL Prover assesses the semantic correctness of a predicted SQL against the user's intent independently, while Adversarial Refuter uses the ground-truth SQL as evidence to challenge and refine this judgment. On our expert-aligned validation set ROSE-VEC, ROSE achieves the best agreement with human experts, outperforming the next-best metric by nearly 24% in Cohen's Kappa. We also conduct a largescale re-evaluation of 19 NL2SQL methods, revealing four valuable insights. We release ROSE and ROSE-VEC to facilitate more reliable NL2SQL research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。