Holistic Safety and Responsibility Evaluations of Advanced AI Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917646883094528 |
|---|---|
| author | Weidinger, Laura Barnhart, Joslyn Brennan, Jenny Butterfield, Christina Young, Susie Hawkins, Will Hendricks, Lisa Anne Comanescu, Ramona Chang, Oscar Rodriguez, Mikel Beroshi, Jennifer Bloxwich, Dawn Proleev, Lev Chen, Jilin Farquhar, Sebastian Ho, Lewis Gabriel, Iason Dafoe, Allan Isaac, William |
| author_facet | Weidinger, Laura Barnhart, Joslyn Brennan, Jenny Butterfield, Christina Young, Susie Hawkins, Will Hendricks, Lisa Anne Comanescu, Ramona Chang, Oscar Rodriguez, Mikel Beroshi, Jennifer Bloxwich, Dawn Proleev, Lev Chen, Jilin Farquhar, Sebastian Ho, Lewis Gabriel, Iason Dafoe, Allan Isaac, William |
| contents | Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to safety evaluation. In this report, we summarise and share elements of our evolving approach as well as lessons learned for a broad audience. Key lessons learned include: First, theoretical underpinnings and frameworks are invaluable to organise the breadth of risk domains, modalities, forms, metrics, and goals. Second, theory and practice of safety evaluation development each benefit from collaboration to clarify goals, methods and challenges, and facilitate the transfer of insights between different stakeholders and disciplines. Third, similar key methods, lessons, and institutions apply across the range of concerns in responsibility and safety - including established and emerging harms. For this reason it is important that a wide range of actors working on safety evaluation and safety research communities work together to develop, refine and implement novel evaluation approaches and best practices, rather than operating in silos. The report concludes with outlining the clear need to rapidly advance the science of evaluations, to integrate new evaluations into the development and governance of AI, to establish scientifically-grounded norms and standards, and to promote a robust evaluation ecosystem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14068 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Holistic Safety and Responsibility Evaluations of Advanced AI Models Weidinger, Laura Barnhart, Joslyn Brennan, Jenny Butterfield, Christina Young, Susie Hawkins, Will Hendricks, Lisa Anne Comanescu, Ramona Chang, Oscar Rodriguez, Mikel Beroshi, Jennifer Bloxwich, Dawn Proleev, Lev Chen, Jilin Farquhar, Sebastian Ho, Lewis Gabriel, Iason Dafoe, Allan Isaac, William Artificial Intelligence Machine Learning Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to safety evaluation. In this report, we summarise and share elements of our evolving approach as well as lessons learned for a broad audience. Key lessons learned include: First, theoretical underpinnings and frameworks are invaluable to organise the breadth of risk domains, modalities, forms, metrics, and goals. Second, theory and practice of safety evaluation development each benefit from collaboration to clarify goals, methods and challenges, and facilitate the transfer of insights between different stakeholders and disciplines. Third, similar key methods, lessons, and institutions apply across the range of concerns in responsibility and safety - including established and emerging harms. For this reason it is important that a wide range of actors working on safety evaluation and safety research communities work together to develop, refine and implement novel evaluation approaches and best practices, rather than operating in silos. The report concludes with outlining the clear need to rapidly advance the science of evaluations, to integrate new evaluations into the development and governance of AI, to establish scientifically-grounded norms and standards, and to promote a robust evaluation ecosystem. |
| title | Holistic Safety and Responsibility Evaluations of Advanced AI Models |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.14068 |