ABSTRACT Retrieval Augmented Generation (RAG) has become a dominant approach for question answering over large collections of unstructured documents. The UDA (Unstructured Document Analysis) benchmark provides a rigorous suite for evaluating RAG systems on real world long documents. This paper presents a large scale, faithfulness oriented evaluation of Qlik Answers on a UDA subset composed of unstructured PDF reports. A corpus of 136 documents (19,959 pages) and 11,842 questi

Author: Igor Alcantara A deep dive into Talend Data Quality’s matching magic, from T-Swoosh to Survivorship If you have been following my series on the theory behind Qlik, you know we usually spend our time analyzing data that is already nicely polished. We look at averages, distributions, machine learning, LLMs, RAG, and charts. However, every developer knows the dark secret of our industry, which is that data is rarely polished when it arrives at our doorstep. It is usually

From Arcade to Analytics, Player One is Data In this short edition of Lund Dialogs, hosts Igor Alcantara and Angelika Klidas sit down with Kazutaka Yorozu , a Qlik Luminary from SEGA , to talk about data and its role in today’s organizations. Recorded in Lund, Sweden, the conversation explores how data supports decision-making, shapes strategy, and influences the way teams think and operate in a competitive environment, from a global perspective grounded in real-world ex