Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.04427 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915634053382144 |
|---|---|
| author | Wang, Xixi Costa, Miguel Kovaceva, Jordanka Wang, Shuai Pereira, Francisco C. |
| author_facet | Wang, Xixi Costa, Miguel Kovaceva, Jordanka Wang, Shuai Pereira, Francisco C. |
| contents | Large language models (LLMs) have shown promise in table Question Answering (Table QA). However, extending these capabilities to multi-table QA remains challenging due to unreliable schema linking across complex tables. Existing methods based on semantic similarity work well only on simplified hand-crafted datasets and struggle to handle complex, real-world scenarios with numerous and diverse columns. To address this, we propose a graph-based framework that leverages human-curated relational knowledge to explicitly encode schema links and join paths. Given a natural language query, our method searches on graph to construct interpretable reasoning chains, aided by pruning and sub-path merging strategies to enhance efficiency and coherence. Experiments on both standard benchmarks and a realistic, large-scale dataset demonstrate the effectiveness of our approach. To our knowledge, this is the first multi-table QA system applied to truly complex industrial tabular data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04427 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance Wang, Xixi Costa, Miguel Kovaceva, Jordanka Wang, Shuai Pereira, Francisco C. Artificial Intelligence Computation and Language Large language models (LLMs) have shown promise in table Question Answering (Table QA). However, extending these capabilities to multi-table QA remains challenging due to unreliable schema linking across complex tables. Existing methods based on semantic similarity work well only on simplified hand-crafted datasets and struggle to handle complex, real-world scenarios with numerous and diverse columns. To address this, we propose a graph-based framework that leverages human-curated relational knowledge to explicitly encode schema links and join paths. Given a natural language query, our method searches on graph to construct interpretable reasoning chains, aided by pruning and sub-path merging strategies to enhance efficiency and coherence. Experiments on both standard benchmarks and a realistic, large-scale dataset demonstrate the effectiveness of our approach. To our knowledge, this is the first multi-table QA system applied to truly complex industrial tabular data. |
| title | Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2506.04427 |