PulseAugur
EN
LIVE 05:40:05

New FICO system improves spreadsheet question answering accuracy

By PulseAugur Editorial · [1 sources] ·

Researchers have introduced FICO (Find-Then-Compute), a novel system designed for question answering over large collections of spreadsheets. FICO first retrieves relevant document summaries and then disambiguates similar workbooks before executing precise Structured Query Language (SQL) queries on the selected full table. The system achieved 76.2% accuracy on the DataBench dataset, outperforming a strong TableRAG-style baseline by 9.9 points. FICO also demonstrated significant gains on the MiMoTable dataset, reaching 79.7% accuracy compared to 22.2% for prefix RAG, highlighting the importance of integrating semantic source selection with exact computation. AI

IMPACT This system could significantly improve how users query and extract information from large collections of spreadsheets, enhancing data analysis workflows.

RANK_REASON The cluster contains a research paper detailing a new system and its performance on benchmarks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New FICO system improves spreadsheet question answering accuracy

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a research paper detailing a new system and its performance on benchmarks. [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.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Kang Li ·

    FICO: Find-Then-Compute for Corpus-Level Spreadsheet Question Answering

    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…

RELATED ENTITIES

RELATED TOPICS