Tag
The paper introduces Operation-wise TableQA, a new task with fine-grained question taxonomy, and proposes SkillTGR, a skill-augmented table graph reasoning framework that uses graph traversal and a hierarchical SkillBank for self-evolving reasoning, achieving superior performance and efficiency.
GRAB uses a GNN encoder to convert relational tables into latent tokens for frozen LLMs, achieving significant performance gains in multi-table question answering.