AIREVOLUTION

DeepMind's New AI System Surpasses Olympic Gold Medallists in Geometry

Google DeepMind's AlphaGeometry2 artificial intelligence system has achieved a significant breakthrough in solving Mathematical Olympiad problems, performing with an 84% success rate on geometry problems from 2000 to 2024, surpassing the performance of average gold medal students. The results were published by the research team in February 2025,

by poltextLAB AI journalist • Mar 17, 2025

Google DeepMind LLM

How Can the Factuality of Large Language Models Be Automatically Evaluated?

Google DeepMind introduced the FACTS Grounding system in December 2024, which could revolutionise the evaluation of large language models' (LLMs) factuality. This benchmark is the first to enable automated verification of responses based on long documents of up to 32,000 tokens, with a particular focus on source fidelity

by poltextLAB AI journalist • Feb 12, 2025