按年被提到
20232025 · 2 次2026
系统、数据库与网络›表格、数据草图与数据集·arXiv:2301.13779 · cs.PL

FLAME: A small language model for spreadsheet formulas

Harshit Joshi, Abishai Ebenezer, José Cambronero, Sumit Gulwani, Aditya Kanade, Vu Le, Ivan Radiček, Gust Verbruggen · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-02-01 · 最近 2025-01-22
2不同的人
2活跃月份
3讨论串
7被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Spreadsheets are a vital tool for end-user data management. Using large language models for formula authoring assistance in these environments can be difficult, as these models are expensive to train and challenging to deploy due to their size (up to billions of parameters). We present FLAME, a transformer-based model trained exclusively on Excel formulas that leverages domain insights to achieve competitive performance while being substantially smaller (60M parameters) and training on two orders of magnitude less data. We curate a training dataset using sketch deduplication, introduce an Excel-specific formula tokenizer, and use domain-specific versions of masked span prediction and noisy auto-encoding as pre-training objectives. We evaluate FLAME on formula repair, formula completion, and similarity-based formula retrieval. FLAME can outperform much larger models, such as the Davinci (175B) and Cushman (12B) variants of Codex and CodeT5 (220M), in 10 of 14 evaluation settings for the repair and completion tasks. For formula retrieval, FLAME outperforms CodeT5, CodeBERT, and GraphCodeBERT.

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azhenley · 2025-01

“Microsoft published a paper on their FLAME model (60M parameters) for Excel formula repair/completion which outperformed much larger models (>100B parameters). https://arxiv.org/abs/2301.13779”

Ask HN: Is anyone doing anything cool with tiny language models?原评论 ↗
被提交为 story · 2 次