Information-retrieval

This post explores RAPTOR, a novel approach to retrieval-augmented language models that constructs a hierarchical tree structure of documents through recursive embedding, clustering, and summarization. This method enables retrieval of information at different levels of abstraction, significantly improving performance on complex question answering tasks involving long documents compared to traditional contiguous chunk retrieval.

KGGen is a Python library that leverages language models to extract high-quality knowledge graphs from plain text. It introduces entity clustering to reduce sparsity and outperforms existing tools on the new MINE benchmark.

Explore the impact of different retrieval strategies on the performance and efficiency of Retrieval-Augmented Generation (RAG) systems in downstream tasks like Question Answering (QA) and attributed QA.

Cohere's Rerank 3.5 is an advanced AI search model designed to enhance the accuracy and relevance of information retrieval in complex enterprise environments.

This post summarizes the key concepts and ideas from the paper 'Agentic Information Retrieval' by Weinan Zhang, Junwei Liao, Ning Li, and Kounianhua Du from Shanghai Jiao Tong University.