A framework to enhance LLMs' understanding of abstraction.
― 5 min read
Hongming Zhang
A new method improves how AI models express their confidence in answers.
― 6 min read
Exploring the need for retrieval systems to understand user perspectives.
― 5 min read
DocBench benchmarks LLM-based systems for reading and responding to various document formats.
― 4 min read
A new method enhances the retrieval of scientific documents.
― 5 min read
A new approach to measure data difficulty for better model training.
― 7 min read
Cognitive Kernel is an open-source system that autonomously handles tasks and gathers information.
― 5 min read
New methods improve large language models' handling of context for better performance.
― 6 min read