arXiv cs.CL· Arjun Rao, Nishant Gopinath·· 10 小时前AI 评分29
FERN：面向 Text-to-SQL 的跨基准表格检索，用冻结检索器与学习排序
FERN: Cross-Benchmark Table Retrieval for Text-to-SQL with Frozen Retrievers and Learned Ranking
AI 导读
FERN 用三个冻结检索器融合出 100 个候选表、每个候选最多 120 个特征，再由 LightGBM 排序器重排，全程不调用生成式 LLM。在未参与拟合的 Spider 上，其候选池在 15 表时召回达 98.0，排序器把 complete@5 从 83.9% 提升到 95.6%。BIRD dev 上单张 A100 每题中位延迟 208 ms，且无需调用托管模型。
正文 · 原文
Abstract:Text-to-SQL systems over large pooled catalogs must first retrieve the tables a question needs. We compare against the published table recall of RASL, which uses Claude 3.5 models to extract keywords and select tables, on pooled BIRD, Spider, and Fiben catalogs. FERN (Feature-Engineered Ranking with No generative LLM) instead fuses three frozen retrievers into 100 candidates, describes each with up to 120 features, and reorders them with LightGBM rankers fitted once on BIRD's training questions. On Spider, where it was not fitted, its candidate pool alone reaches RASL's published recall at fifteen tables (98.0), and the ranker raises the share of questions with every gold table in the top five (complete@5) from 83.9% to 95.6%. At five tables, FERN's recall is within one point of RASL's on Spider (96.7 vs 97.0) and on BIRD with its evidence hints (96.6 vs 97.5), and 8.2 points below on BIRD without them (89.3). On 121 real BEAVER questions, without BEAVER fitting, its recall at fifteen (82.1) falls between two BEAVER-trained retrievers (80.8, 84.5), but its complete@15 is below both (49.6 vs 54.5 and 62.0). On Fiben, it falls far short at fifteen tables (54.2 vs 69.2, different question sets), although its recall at fifty is numerically close to RASL's question-only retrieval result (80.7 vs 79.4). On BIRD dev with evidence, non-retrieval features raise complete@5 by 7.7 points over retrieval signals alone. On BIRD dev, median latency is 208 ms per question on one A100, without hosted model calls.
| Comments: | 19 pages |
| Subjects: | Information Retrieval (cs.IR); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.14477 [cs.IR] |
| (or arXiv:2611.14477v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14477 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Arjun Sathiyanarayana Rao [view email]
[v1]
Tue, 10 Nov 2026 18:39:49 UTC (25 KB)
来源：arXiv cs.CL · arxiv.org