Scholarlink

The paper presents MammoTab 25, a new dataset comprising approximately 838930 Wikipedia tables extracted from over 63 million English Wikipedia pages and semantically annotated through Wikidata. Each table in MammoTab 25 is accompanied by fine-grained metadata, including column typing, NIL flags, and statistics, and by four prompt templates, making the resource simultaneously suitable for training, fine-tuning, and stress-testing Large Language Models (LLMs). MammoTab 25 covers, in a single benchmark, all key challenges for the semantic interpretation of tables, such as disambiguation issues, homonymy and acronym presence, NIL-mentions, and large web-table sizes; the tags attached to every table let researchers isolate and diagnose specific failure cases with precision. The corpus is delivered with an open-source pipeline that can be rerun on future Wikipedia dumps, ensuring long-term sustainability and up-to-date annotations. MammoTab 25 already supports, and will continue to support, a public leaderboard that evaluates the Semantic Table Interpretation (STI) capabilities of state-of-the-art and upcoming LLMs, providing the community with a live yardstick of progress. Resource Type: Dataset License: GNU Affero General Public License v3.0 DOI: https://doi.org/10.5281/zenodo.16562700 URL: https://github.com/unimib-datAI/mammotab/ Website/Documentation: https://unimib-datai.github.io/mammotab-docs/

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MammoTab 25: A Large-Scale Dataset for Semantic Table Interpretation - Training, Testing, and Detecting Weaknesses

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Marco Cremaschi,
  • Federico Belotti,
  • Jennifer D’Souza,
  • Matteo Palmonari

摘要

The paper presents MammoTab 25, a new dataset comprising approximately 838930 Wikipedia tables extracted from over 63 million English Wikipedia pages and semantically annotated through Wikidata. Each table in MammoTab 25 is accompanied by fine-grained metadata, including column typing, NIL flags, and statistics, and by four prompt templates, making the resource simultaneously suitable for training, fine-tuning, and stress-testing Large Language Models (LLMs). MammoTab 25 covers, in a single benchmark, all key challenges for the semantic interpretation of tables, such as disambiguation issues, homonymy and acronym presence, NIL-mentions, and large web-table sizes; the tags attached to every table let researchers isolate and diagnose specific failure cases with precision. The corpus is delivered with an open-source pipeline that can be rerun on future Wikipedia dumps, ensuring long-term sustainability and up-to-date annotations. MammoTab 25 already supports, and will continue to support, a public leaderboard that evaluates the Semantic Table Interpretation (STI) capabilities of state-of-the-art and upcoming LLMs, providing the community with a live yardstick of progress. Resource Type: Dataset License: GNU Affero General Public License v3.0 DOI: https://doi.org/10.5281/zenodo.16562700 URL: https://github.com/unimib-datAI/mammotab/ Website/Documentation: https://unimib-datai.github.io/mammotab-docs/