4 papers
Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations
Igor Fedorov, Kate Plawiak, Lemeng Wu +17
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. We demonstrate that Lla…
Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG
Chenhao Fang, Derek Larson, Shitong Zhu +9
This paper presents new methods that have the potential to improve privacy process efficiency with LLM and RAG. To reduce hallucination, we continually pre-train the base LLM model…
SCOUT: simultaneous time segmentation and community detection in dynamic networks
Yuriy Hulovatyy, Tijana Milenkovic
Many evolving complex systems can be modeled via dynamic networks. An important problem in dynamic network research is community detection, which identifies groups of topologically…
Exploring the structure and function of temporal networks with dynamic graphlets
Yuriy Hulovatyy, Huili Chen, Tijana Milenkovic
With the growing amount of available temporal real-world network data, an important question is how to efficiently study these data. One can simply model a temporal network as eith…