Automatic Generation of Model and Data Cards: A Step Towards Responsible AI. Liu, J., Li, W., Jin, Z., & Diab, M. May, 2024. ![Automatic Generation of Model and Data Cards: A Step Towards Responsible AI [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex In an era of model and data proliferation in machine learning/AI especially marked by the rapid advancement of open-sourced technologies, there arises a critical need for standardized consistent documentation. Our work addresses the information incompleteness in current human-generated model and data cards. We propose an automated generation approach using Large Language Models (LLMs). Our key contributions include the establishment of CardBench, a comprehensive dataset aggregated from over 4.8k model cards and 1.4k data cards, coupled with the development of the CardGen pipeline comprising a two-step retrieval process. Our approach exhibits enhanced completeness, objectivity, and faithfulness in generated model and data cards, a significant step in responsible AI documentation practices ensuring better accountability and traceability.
@misc{liu_automatic_2024,
title = {Automatic {Generation} of {Model} and {Data} {Cards}: {A} {Step} {Towards} {Responsible} {AI}},
shorttitle = {Automatic {Generation} of {Model} and {Data} {Cards}},
url = {https://arxiv.org/abs/2405.06258v2},
abstract = {In an era of model and data proliferation in machine learning/AI especially marked by the rapid advancement of open-sourced technologies, there arises a critical need for standardized consistent documentation. Our work addresses the information incompleteness in current human-generated model and data cards. We propose an automated generation approach using Large Language Models (LLMs). Our key contributions include the establishment of CardBench, a comprehensive dataset aggregated from over 4.8k model cards and 1.4k data cards, coupled with the development of the CardGen pipeline comprising a two-step retrieval process. Our approach exhibits enhanced completeness, objectivity, and faithfulness in generated model and data cards, a significant step in responsible AI documentation practices ensuring better accountability and traceability.},
language = {en},
urldate = {2024-09-03},
journal = {arXiv.org},
author = {Liu, Jiarui and Li, Wenkai and Jin, Zhijing and Diab, Mona},
month = may,
year = {2024},
}
Downloads: 0
{"_id":"9Mmmca88N285CZ2Bf","bibbaseid":"liu-li-jin-diab-automaticgenerationofmodelanddatacardsasteptowardsresponsibleai-2024","author_short":["Liu, J.","Li, W.","Jin, Z.","Diab, M."],"bibdata":{"bibtype":"misc","type":"misc","title":"Automatic Generation of Model and Data Cards: A Step Towards Responsible AI","shorttitle":"Automatic Generation of Model and Data Cards","url":"https://arxiv.org/abs/2405.06258v2","abstract":"In an era of model and data proliferation in machine learning/AI especially marked by the rapid advancement of open-sourced technologies, there arises a critical need for standardized consistent documentation. Our work addresses the information incompleteness in current human-generated model and data cards. We propose an automated generation approach using Large Language Models (LLMs). Our key contributions include the establishment of CardBench, a comprehensive dataset aggregated from over 4.8k model cards and 1.4k data cards, coupled with the development of the CardGen pipeline comprising a two-step retrieval process. Our approach exhibits enhanced completeness, objectivity, and faithfulness in generated model and data cards, a significant step in responsible AI documentation practices ensuring better accountability and traceability.","language":"en","urldate":"2024-09-03","journal":"arXiv.org","author":[{"propositions":[],"lastnames":["Liu"],"firstnames":["Jiarui"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Wenkai"],"suffixes":[]},{"propositions":[],"lastnames":["Jin"],"firstnames":["Zhijing"],"suffixes":[]},{"propositions":[],"lastnames":["Diab"],"firstnames":["Mona"],"suffixes":[]}],"month":"May","year":"2024","bibtex":"@misc{liu_automatic_2024,\n\ttitle = {Automatic {Generation} of {Model} and {Data} {Cards}: {A} {Step} {Towards} {Responsible} {AI}},\n\tshorttitle = {Automatic {Generation} of {Model} and {Data} {Cards}},\n\turl = {https://arxiv.org/abs/2405.06258v2},\n\tabstract = {In an era of model and data proliferation in machine learning/AI especially marked by the rapid advancement of open-sourced technologies, there arises a critical need for standardized consistent documentation. Our work addresses the information incompleteness in current human-generated model and data cards. We propose an automated generation approach using Large Language Models (LLMs). Our key contributions include the establishment of CardBench, a comprehensive dataset aggregated from over 4.8k model cards and 1.4k data cards, coupled with the development of the CardGen pipeline comprising a two-step retrieval process. Our approach exhibits enhanced completeness, objectivity, and faithfulness in generated model and data cards, a significant step in responsible AI documentation practices ensuring better accountability and traceability.},\n\tlanguage = {en},\n\turldate = {2024-09-03},\n\tjournal = {arXiv.org},\n\tauthor = {Liu, Jiarui and Li, Wenkai and Jin, Zhijing and Diab, Mona},\n\tmonth = may,\n\tyear = {2024},\n}\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["Liu, J.","Li, W.","Jin, Z.","Diab, M."],"key":"liu_automatic_2024","id":"liu_automatic_2024","bibbaseid":"liu-li-jin-diab-automaticgenerationofmodelanddatacardsasteptowardsresponsibleai-2024","role":"author","urls":{"Paper":"https://arxiv.org/abs/2405.06258v2"},"metadata":{"authorlinks":{}}},"bibtype":"misc","biburl":"https://bibbase.org/zotero-group/schulzkx/5158478","dataSources":["JFDnASMkoQCjjGL8E"],"keywords":[],"search_terms":["automatic","generation","model","data","cards","step","towards","responsible","liu","li","jin","diab"],"title":"Automatic Generation of Model and Data Cards: A Step Towards Responsible AI","year":2024}