paper7Updated Nov 21, 2026 · Português
← All papers

Visconde: Multi-document QA with GPT-3 and Neural Reranking

Jayr Pereira, Robson Fidalgo, Roberto Lotufo, Rodrigo Nogueira

Abstract

This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate. The first step decomposes the question into simpler questions using a few-shot large language model (LLM). Then, a state-of-the-art search engine is used to retrieve candidate passages from a large collection for each decomposed question. In the final step, we use the LLM in a few-shot setting to aggregate the contents of the passa…

Who it is from

Other papers from the same organizations