ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
Paper
•
2404.08676
•
Published
•
3
SafeLMM
community
AI & ML interests
Synthetic Augmented data, Fair and Extreme-scaled Large Multimodal Model (SafeLMM) * Multilingual, Multimodal, Multidomain data * Synthetic data * Safety-by-design
Recent Activity
View all activity
SafeLMM's activity
huu-ontocord
authored
a
paper
8 months ago
tanmaylaud
authored
3
papers
9 months ago
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Paper
•
2404.00399
•
Published
•
41
ClimaBench: A Benchmark Dataset For Climate Change Text Understanding in English
Paper
•
2301.04253
•
Published
•
1
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Paper
•
2211.05100
•
Published
•
27
huu-ontocord
posted
an
update
9 months ago
Post
1639
We would like to announce our Aurora-M multilingual models which is based on Starcoderplus.
Twitter: https://twitter.com/ontocord/status/1772778544051155029
LinkedIn: https://www.linkedin.com/feed/update/urn:li:activity:7178521998845759488/
Blog post: https://huggingface.co/blog/mayank-mishra/aurora
Arxiv: Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order (2404.00399)
Current LLMs are very susceptible to generating toxic, harmful and even dangerous content. They can also generate outputs with gender or racial biases. The Biden-Harris Executive Order https://www.federalregister.gov/documents/2023/11/01/2023-24283/safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence) sets forth guidelines on what is considered a safe AI system.
Following up on these guidelines, we present the world's first open source Biden-Harris Executive Order Red teamed Multilingual Language Model: Aurora-M. Inspired by BigScience, the model is trained on 5 languages: English, Hindi, Japanese, Vietnamese and Finnish.
* Red teamed model: aurora-m/aurora-m-biden-harris-redteamed tuned according to the order mentioned above)
* Base model: aurora-m/aurora-m-base (not safety tuned)
* Instruct model: aurora-m/aurora-m-instruct (not safety tuned)
@mayank-mishra @cabbage972 @sted97 @Xa9aX @Taishi-N324 @Muennighoff @vumichien @prateeky2806 @felfri @spyysalo and many many others!
Twitter: https://twitter.com/ontocord/status/1772778544051155029
LinkedIn: https://www.linkedin.com/feed/update/urn:li:activity:7178521998845759488/
Blog post: https://huggingface.co/blog/mayank-mishra/aurora
Arxiv: Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order (2404.00399)
Current LLMs are very susceptible to generating toxic, harmful and even dangerous content. They can also generate outputs with gender or racial biases. The Biden-Harris Executive Order https://www.federalregister.gov/documents/2023/11/01/2023-24283/safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence) sets forth guidelines on what is considered a safe AI system.
Following up on these guidelines, we present the world's first open source Biden-Harris Executive Order Red teamed Multilingual Language Model: Aurora-M. Inspired by BigScience, the model is trained on 5 languages: English, Hindi, Japanese, Vietnamese and Finnish.
* Red teamed model: aurora-m/aurora-m-biden-harris-redteamed tuned according to the order mentioned above)
* Base model: aurora-m/aurora-m-base (not safety tuned)
* Instruct model: aurora-m/aurora-m-instruct (not safety tuned)
@mayank-mishra @cabbage972 @sted97 @Xa9aX @Taishi-N324 @Muennighoff @vumichien @prateeky2806 @felfri @spyysalo and many many others!
huu-ontocord
authored
3
papers
9 months ago
OpenAssistant Conversations -- Democratizing Large Language Model Alignment
Paper
•
2304.07327
•
Published
•
5
Data Governance in the Age of Large-Scale Data-Driven Language Technology
Paper
•
2206.03216
•
Published
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Paper
•
2404.00399
•
Published
•
41