Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning

Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods rely on task-specific strategies or bespoke representations, which hinder their ability to dismantle barriers between different SKR tasks, thereby constraining their overall performance in cross-task scenarios. In this paper, we introduce Pandora, a novel USKR framework that addresses the limitations of existing methods by leveraging two key innovations. First, we propose a code-based unified knowledge representation using Python's Pandas API, which aligns seamlessly with the pre-training of LLMs. This representation facilitates a cohesive approach to handling different structured knowledge sources. Building on this foundation, we employ knowledge transfer to bolster the unified reasoning process of LLMs by automatically building cross-task memory. By adaptively correcting reasoning using feedback from code execution, Pandora showcases impressive unified reasoning capabilities. Extensive experiments on six widely used benchmarks across three SKR tasks demonstrate that Pandora outperforms existing unified reasoning frameworks and competes effectively with task-specific methods.