Search Results for author:
Found 8 papers, 2 papers with code
Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations
This paper presents Llama Guard 3-1B-INT4, a compact and efficient Llama Guard model, which has been open-sourced to the community during Meta Connect 2024.
Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations
We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multimodal LLM inputs (prompt classification) and outputs (response classification).
Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale
Our initial findings show that translation quality for EN-to-XX translations is an average of 8 spBLEU better when evaluating with the masculine human reference compared to feminine.
Polyhedral geometry and combinatorics of an autocatalytic ecosystem
Developing a mathematical understanding of autocatalysis in reaction networks has both theoretical and practical implications.
Toxicity in Multilingual Machine Translation at Scale
We evaluate and analyze added toxicity when translating a large evaluation dataset (HOLISTICBIAS, over 472k sentences, covering 13 demographic axes) from English into 164 languages.
Perturbation Augmentation for Fairer NLP
Unwanted and often harmful social biases are becoming ever more salient in NLP research, affecting both models and datasets.
Multiple-Attribute Text Rewriting
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
