论文标题
Visconde：具有GPT-3和Neural Reranking的多文件质量图
Visconde: Multi-document QA with GPT-3 and Neural Reranking
论文作者
论文摘要
本文提出了一个提问系统，该系统可以回答其支持证据的问题分布在多个（潜在的）文档上。该系统称为Visconde，使用三步管道来执行任务：分解，检索和聚合。第一步使用一些大型语言模型（LLM）将问题分解为更简单的问题。然后，使用最先进的搜索引擎来从一个大型收藏中检索候选段落，以解决每个分解问题。在最后一步中，我们在几次设置中使用LLM将段落的内容汇总到最终答案中。该系统在三个数据集上进行评估：IIRC，QASPER和StrategionQA。结果表明，当前的猎犬是主要的瓶颈，只要提供相关段落，读者就已经在人类水平上表演。当诱使该模型在回答问题之前引起解释时，该系统也会更有效。代码可在\ url {https://github.com/neuralmind-ai/visconde}中找到。
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 passages into the final answer. The system is evaluated on three datasets: IIRC, Qasper, and StrategyQA. Results suggest that current retrievers are the main bottleneck and that readers are already performing at the human level as long as relevant passages are provided. The system is also shown to be more effective when the model is induced to give explanations before answering a question. Code is available at \url{https://github.com/neuralmind-ai/visconde}.
