To Err is AI : A Case Study Informing LLM Flaw Reporting Practices
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910652266708992 |
|---|---|
| author | McGregor, Sean Ettinger, Allyson Judd, Nick Albee, Paul Jiang, Liwei Rao, Kavel Smith, Will Longpre, Shayne Ghosh, Avijit Fiorelli, Christopher Hoang, Michelle Cattell, Sven Dziri, Nouha |
| author_facet | McGregor, Sean Ettinger, Allyson Judd, Nick Albee, Paul Jiang, Liwei Rao, Kavel Smith, Will Longpre, Shayne Ghosh, Avijit Fiorelli, Christopher Hoang, Michelle Cattell, Sven Dziri, Nouha |
| contents | In August of 2024, 495 hackers generated evaluations in an open-ended bug bounty targeting the Open Language Model (OLMo) from The Allen Institute for AI. A vendor panel staffed by representatives of OLMo's safety program adjudicated changes to OLMo's documentation and awarded cash bounties to participants who successfully demonstrated a need for public disclosure clarifying the intent, capacities, and hazards of model deployment. This paper presents a collection of lessons learned, illustrative of flaw reporting best practices intended to reduce the likelihood of incidents and produce safer large language models (LLMs). These include best practices for safety reporting processes, their artifacts, and safety program staffing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12104 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | To Err is AI : A Case Study Informing LLM Flaw Reporting Practices McGregor, Sean Ettinger, Allyson Judd, Nick Albee, Paul Jiang, Liwei Rao, Kavel Smith, Will Longpre, Shayne Ghosh, Avijit Fiorelli, Christopher Hoang, Michelle Cattell, Sven Dziri, Nouha Computers and Society Machine Learning Software Engineering In August of 2024, 495 hackers generated evaluations in an open-ended bug bounty targeting the Open Language Model (OLMo) from The Allen Institute for AI. A vendor panel staffed by representatives of OLMo's safety program adjudicated changes to OLMo's documentation and awarded cash bounties to participants who successfully demonstrated a need for public disclosure clarifying the intent, capacities, and hazards of model deployment. This paper presents a collection of lessons learned, illustrative of flaw reporting best practices intended to reduce the likelihood of incidents and produce safer large language models (LLMs). These include best practices for safety reporting processes, their artifacts, and safety program staffing. |
| title | To Err is AI : A Case Study Informing LLM Flaw Reporting Practices |
| topic | Computers and Society Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2410.12104 |