按年被提到
20242024 · 5 次2026
系统、数据库与网络›表格、数据草图与数据集·arXiv:2407.09025 · cs.AI

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Haoyu Dong, Jianbo Zhao, Yuzhang Tian, Junyu Xiong, Shiyu Xia, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 6 人首次 2024-07-15 · 最近 2025-06-23
6不同的人
2活跃月份
6讨论串
19被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts, and varied formatting options, which pose significant challenges for large language models (LLMs). In response, we introduce SpreadsheetLLM, pioneering an efficient encoding method designed to unleash and optimize LLMs' powerful understanding and reasoning capability on spreadsheets. Initially, we propose a vanilla serialization approach that incorporates cell addresses, values, and formats. However, this approach was limited by LLMs' token constraints, making it impractical for most applications. To tackle this challenge, we develop SheetCompressor, an innovative encoding framework that compresses spreadsheets effectively for LLMs. It comprises three modules: structural-anchor-based compression, inverse index translation, and data-format-aware aggregation. It significantly improves performance in the spreadsheet table detection task, outperforming the vanilla approach by 25.6% in GPT4's in-context learning setting. Moreover, fine-tuned LLM with SheetCompressor has an average compression ratio of 25 times, and achieves a state-of-the-art 78.9% F1 score, surpassing the best existing models by 12.3%. Finally, we propose Chain of Spreadsheet for downstream tasks of spreadsheet understanding and validate it in a new and demanding spreadsheet QA task. We methodically leverage the inherent layout and structure of spreadsheets, demonstrating that SpreadsheetLLM is highly effective across a variety of spreadsheet tasks.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论michaelmior · 2024-07

“SpreadsheetLLM[0] might be worth looking into. It's designed for Excel (and similar) spreadsheets, so I'd imagine you could do something far simpler for the majority of HTML tables. [0] https://arxiv.org/abs/2407.09025v1”

Show HN: Convert HTML DOM to semantic markdown for use in LLMs原评论 ↗
评论jhuguet · 2025-06

“Founder of anyformat.ai here, building from Madrid, Spain, with a specific focus on Europe and its unique market and regulation dynamics. Just want to say how energizing it is to see this space maturing through thoughtful products like Extend and Reducto. Congrats to both for your Series A. I’d also mention GetOmni, as they’re doing great work leading th…”

Launch HN: Reducto Studio (YC W24) – Build accurate document pipelines, fast原评论 ↗
被提交为 story · 4 次