Model
Phi-4
2 stories mentioning Phi-4, newest first, each with its sources and discussion. Follow to see new ones on your front page.
-
Experiment: Graph RAG outperforms standard RAG on multi-hop questions, but frontier models lead
A hands-on experiment compared four AI retrieval architectures using a small dataset of two Anthropic articles on AI security. The systems tested were Plain RAG, Graph-Only retrieval, hybrid Graph RAG, and a…
1 sourceTowards Data Science -
GTA agent and GT Bench improve LLM graph reasoning accuracy
Researchers have introduced Graph Theory Bench (GT Bench), a comprehensive evaluation suite designed to test Large Language Models on complex graph reasoning tasks. The benchmark covers 24 classical graph problems…
2 sources primary sourcearXiv cs.AI
Questions about Phi-4
What is the latest news about Phi-4?
Experiment: Graph RAG outperforms standard RAG on multi-hop questions, but frontier models lead (17 September 2026).