SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing
This addresses the problem of accurate question answering for users needing information from diverse sources, though it appears incremental as it builds on existing hybrid methods.
The paper tackles open-domain question answering from heterogeneous data sources by introducing SPAGHETTI, a hybrid pipeline that achieves a state-of-the-art 56.5% exact match rate on the Compmix dataset, with manual analysis suggesting over 90% accuracy.
We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including knowledge base, text, tables, and infoboxes. Our LLM-augmented approach achieves state-of-the-art performance on the Compmix dataset, the most comprehensive heterogeneous open-domain QA dataset, with 56.5% exact match (EM) rate. More importantly, manual analysis on a sample of the dataset suggests that SPAGHETTI is more than 90% accurate, indicating that EM is no longer suitable for assessing the capabilities of QA systems today.