TableRAG: Million-Token Table Understanding with Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916543077548032 |
|---|---|
| author | Chen, Si-An Miculicich, Lesly Eisenschlos, Julian Martin Wang, Zifeng Wang, Zilong Chen, Yanfei Fujii, Yasuhisa Lin, Hsuan-Tien Lee, Chen-Yu Pfister, Tomas |
| author_facet | Chen, Si-An Miculicich, Lesly Eisenschlos, Julian Martin Wang, Zifeng Wang, Zilong Chen, Yanfei Fujii, Yasuhisa Lin, Hsuan-Tien Lee, Chen-Yu Pfister, Tomas |
| contents | Recent advancements in language models (LMs) have notably enhanced their ability to reason with tabular data, primarily through program-aided mechanisms that manipulate and analyze tables. However, these methods often require the entire table as input, leading to scalability challenges due to the positional bias or context length constraints. In response to these challenges, we introduce TableRAG, a Retrieval-Augmented Generation (RAG) framework specifically designed for LM-based table understanding. TableRAG leverages query expansion combined with schema and cell retrieval to pinpoint crucial information before providing it to the LMs. This enables more efficient data encoding and precise retrieval, significantly reducing prompt lengths and mitigating information loss. We have developed two new million-token benchmarks from the Arcade and BIRD-SQL datasets to thoroughly evaluate TableRAG's effectiveness at scale. Our results demonstrate that TableRAG's retrieval design achieves the highest retrieval quality, leading to the new state-of-the-art performance on large-scale table understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04739 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TableRAG: Million-Token Table Understanding with Language Models Chen, Si-An Miculicich, Lesly Eisenschlos, Julian Martin Wang, Zifeng Wang, Zilong Chen, Yanfei Fujii, Yasuhisa Lin, Hsuan-Tien Lee, Chen-Yu Pfister, Tomas Computation and Language Artificial Intelligence Information Retrieval Machine Learning Recent advancements in language models (LMs) have notably enhanced their ability to reason with tabular data, primarily through program-aided mechanisms that manipulate and analyze tables. However, these methods often require the entire table as input, leading to scalability challenges due to the positional bias or context length constraints. In response to these challenges, we introduce TableRAG, a Retrieval-Augmented Generation (RAG) framework specifically designed for LM-based table understanding. TableRAG leverages query expansion combined with schema and cell retrieval to pinpoint crucial information before providing it to the LMs. This enables more efficient data encoding and precise retrieval, significantly reducing prompt lengths and mitigating information loss. We have developed two new million-token benchmarks from the Arcade and BIRD-SQL datasets to thoroughly evaluate TableRAG's effectiveness at scale. Our results demonstrate that TableRAG's retrieval design achieves the highest retrieval quality, leading to the new state-of-the-art performance on large-scale table understanding. |
| title | TableRAG: Million-Token Table Understanding with Language Models |
| topic | Computation and Language Artificial Intelligence Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2410.04739 |