Goto

Collaborating Authors

 intelligent car


CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity

arXiv.org Artificial Intelligence

Retrieval-Augmented Generation (RAG) aims to enhance large language models (LLMs) to generate more accurate and reliable answers with the help of the retrieved context from external knowledge sources, thereby reducing the incidence of hallucinations. Despite the advancements, evaluating these systems remains a crucial research area due to the following issues: (1) Limited data diversity: The insufficient diversity of knowledge sources and query types constrains the applicability of RAG systems; (2) Obscure problems location: Existing evaluation methods have difficulty in locating the stage of the RAG pipeline where problems occur; (3) Unstable retrieval evaluation: These methods often fail to effectively assess retrieval performance, particularly when the chunking strategy changes. To tackle these challenges, we propose a Comprehensive Full-chain Evaluation (CoFE-RAG) framework to facilitate thorough evaluation across the entire RAG pipeline, including chunking, retrieval, reranking, and generation. To effectively evaluate the first three phases, we introduce multi-granularity keywords, including coarse-grained and fine-grained keywords, to assess the retrieved context instead of relying on the annotation of golden chunks. Moreover, we release a holistic benchmark dataset tailored for diverse data scenarios covering a wide range of document formats and query types. We demonstrate the utility of the CoFE-RAG framework by conducting experiments to evaluate each stage of RAG systems. Our evaluation method provides unique insights into the effectiveness of RAG systems in handling diverse data scenarios, offering a more nuanced understanding of their capabilities and limitations.


Driverless: Intelligent Cars and the Road Ahead (MIT Press): Hod Lipson, Melba Kurman: 9780262035224: Amazon.com: Books

#artificialintelligence

Everyone is talking about driverless cars ... After reading this book, you will be knowledgeable enough to make your own informed opinion. Driverless vehicles are poised to usher in a massive disruption of our transportation system, our urban landscapes, our economy -- and quite possibly the very fabric of society. Anyone who wants to understand what's coming must read this fascinating book. Driverless is a great read for anybody interested in technological, societal, and ethical implications of self-driving cars. The book reaches across fields and issues thoughtfully, and presents a comprehensive view of the state of the art.


Hyundai, Cisco come together to create 'computers on wheels'

ZDNet

Hyundai Motor Group and Cisco are partnering in a new push to further research in the connected car industry. The South Korean firm has developed a roadmap for connected car development which will eventually lead to the creation of the "hyper-connected and intelligent car" concept. Automakers and tech firms alike, ranging from Apple and Google to Chrysler and General Motors are all focused on innovation in the connected car industry. Autonomous driving, the use of cameras and sensors and internet-connected infotainment dashboards are only some of the developments which have become commercial over the past few years -- and the industry is likely to become a strong revenue generator in the future. In the short term for Hyundai, however, the focus will be on bringing smartphone connectivity and smart home services to vehicles, the firm said in a press release.