The ReQAP System for Question Answering over Personal Information

TL;DR

ReQAP is a system that enables complex question answering over personal data sources by recursively decomposing questions and using lightweight language models for interpretation and execution, enhancing transparency and user trust.

Contribution

It introduces a novel recursive decomposition approach combined with fine-tuned language models for effective question answering over heterogeneous personal data sources.

Findings

Supports complex questions involving filters, joins, and aggregation.

Provides detailed tracking of answer computation for transparency.

Demonstrates rich functionality for advanced user queries.

Abstract

Personal information is abundant on users' devices, from structured data in calendar, shopping records or fitness tools, to unstructured contents in mail and social media posts. This works presents the ReQAP system that supports users with answers for complex questions that involve filters, joins and aggregation over heterogeneous sources. The unique trait of ReQAP is that it recursively decomposes questions and incrementally builds an operator tree for execution. Both the question interpretation and the individual operators make smart use of light-weight language models, with judicious fine-tuning. The demo showcases the rich functionality for advanced user questions, and also offers detailed tracking of how the answers are computed by the operators in the execution tree. Being able to trace answers back to the underlying sources is vital for human comprehensibility and user trust in the system.