Automatic Generation of Model and Data Cards: A Step Towards Responsible AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910495001280512 |
|---|---|
| author | Liu, Jiarui Li, Wenkai Jin, Zhijing Diab, Mona |
| author_facet | Liu, Jiarui Li, Wenkai Jin, Zhijing Diab, Mona |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06258 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatic Generation of Model and Data Cards: A Step Towards Responsible AI Liu, Jiarui Li, Wenkai Jin, Zhijing Diab, Mona Computation and Language 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. |
| title | Automatic Generation of Model and Data Cards: A Step Towards Responsible AI |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.06258 |