English(EN) FICO: Find-Then-Compute for Corpus-Level Spreadsheet Question Answering

新的FICO系统提高了电子表格问答的准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 19:13

研究人员推出FICO（Find-Then-Compute），一个用于大规模电子表格集合问答的新颖系统。FICO首先检索相关的文档摘要，然后在执行精确的结构化查询语言（SQL）查询之前，对相似的工作簿进行消歧。该系统在DataBench数据集上达到了76.2%的准确率，比强大的TableRAG风格基线高出9.9个百分点。FICO在MiMoTable数据集上也取得了显著的进步，准确率达到79.7%，而前缀RAG为22.2%，这凸显了将语义源选择与精确计算相结合的重要性。 AI

影响该系统可以显著改善用户查询和提取大型电子表格集合信息的方式，从而增强数据分析工作流程。

排序理由该集群包含一篇详细介绍新系统及其在基准测试中性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新系统及其在基准测试中性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 5 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Kang Li · 2026-10-02 19:13

FICO：用于语料库级电子表格问答的查找-然后-计算方法

Question answering over spreadsheet collections requires finding the correct workbook and computing over complete tables. We introduce Find-then-Compute (FiCo), which retrieves document summaries, disambiguates similar workbooks, and executes constrained Structured Query Language…

本文如何被排名

报道来源 [1]

FICO：用于语料库级电子表格问答的查找-然后-计算方法

相关实体

相关话题