EASE: Entity-Aware Sub-table Generation for Real-world Multi-table QA

Recent advancements in table-based question answering (table QA) have been driven by the development of table-specific reasoning strategies for leveraging large language models. Previous works employ sub-table-based reasoning, which involves matching queryrelevant table values and aggregating them into sub-tables for precise reasoning. However, these approaches are limited to scenarios with query-relevant single tables, failing to handle real-world table QA settings that involve noisy multi-table sets. To address the challenges of real-world table QA, we propose EASE: Entity-Aware Sub-table Generation for REal-world Multi-table QA framework. Given a noisy multi-table set, EASE first extracts key entities from the question to construct a sub-table schema. It then populates this schema by utilizing a selected set of column values from the noisy multi-table set, thereby facilitating efficient and effective sub-table-based reasoning. We introduce a Noisy Multi-table QA dataset and conduct extensive experiments to evaluate EASE's effectiveness on real-world table QA. Our results demonstrate that EASE effectively filters out irrelevant information while incorporating pertinent table values, leading to efficient and effective performance on real-world table QA. Our dataset can be found https://github.com/Metalchaos8527/ ease_noisy_multi-table_qa.git Reviewer id Lewis 1 Harris 2 amenid dormid 922 109 950 104 932 140 (a) Single-table based LLM Framework Operation Type Sub-Table (b) Naïve Multi-table based Language Modeling Seq2Seq Transformer 10000.0 Answer col: Height row 4: 202.0 ❌ Answer LLM LLM Sub-table Schema Generation (𝐸 ! ) Column Value Selection (𝑇 " ) Sub-table Filling (𝐸 ! # ) Answer Generation (𝐴 % ) The name 'Weeks' contains 'ee'. The corresponding 'id' is 4. The balance for 'id' 4 is 7000.0. The answer is: 7000