Retrieval-Augmented Generation (RAG) synergistically combines the intrinsic knowledge of LLMs with the huge, dynamic databases of companies. Referencing the basic concept of a RAG ("Naive RAG"), this working paper identifies the critical factors of this cutting-edge architecture and gives hints...

We explore an augmented democracy system built on off-the-shelf large language models (LLMs) fine-tuned to augment data on citizens' preferences elicited over policies extracted from the government programmes of the two main candidates of Brazil's 2022 presidential election. We use a train-test...

Large language models (LLMs) are a potential substitute for human-generated data and knowledge resources. This substitution, however, can present a significant problem for the training data needed to develop future models if it leads to a reduction of human-generated content. In this work, we...