About
Research & Development
Unlocking Black-Box Optimization: How GPTOpt Leverages LLMs for Efficiency
TLDR: GPTOpt is a new method that fine-tunes Large Language Models (LLMs) to solve complex black-box optimization problems efficiently. By training LLMs on a...
Research & Development
Reading Between the Lines: How AI’s Understanding of Implied Meaning Shapes Our Digital Conversations
TLDR: This research explores how Large Language Models (LLMs) interpret "implicature" – meaning conveyed beyond explicit statements. It finds that larger LLMs are better...
Research & Development
DcuRAGONs Team’s Winning Strategy for Multilingual E-commerce Search
TLDR: The DcuRAGONs team won the Alibaba International E-commerce Product Search Competition by developing a data-centric methodology. Their approach leveraged multilingual Large Language Models...
Research & Development
Training Proactive Language Models from Real-World Conversations
TLDR: Learn-to-Ask is a novel, simulator-free framework that teaches Large Language Models (LLMs) to be proactive and goal-oriented by learning directly from offline expert...
Research & Development
AI Model Aurora Adapted for Precise Ocean Temperature Forecasting
TLDR: Researchers successfully adapted Aurora, a deep learning model originally for atmospheric forecasting, to predict sea surface temperature in the Canary Upwelling System. By...
Research & Development
E-Scores: A New Approach to Flexible and Reliable Generative Model Output Assessment
TLDR: A new research paper introduces 'e-scores' as a novel method for assessing the correctness of generative model outputs, particularly from large language models...