An overview of challenges and solutions in multilingual search.
― 5 min read
Jonathan May
This study evaluates bias measurement methods using GPT-3.5-Turbo for antisemitism detection.
― 5 min read
Examining how communication skills impact AI performance in the game of Diplomacy.
― 6 min read
Analyzing the storytelling capabilities of large language models compared to human authors.
― 4 min read
A toolkit designed for better evaluation of human-bot interactions.
― 5 min read
Enhancing language models to produce better spoken responses for voice assistants.
― 5 min read
Exploring how AI enhances gameplay in the board game Diplomacy.
― 6 min read