OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929313080672256 |
|---|---|
| author | Kong, Kezhi Zhang, Jiani Shen, Zhengyuan Srinivasan, Balasubramaniam Lei, Chuan Faloutsos, Christos Rangwala, Huzefa Karypis, George |
| author_facet | Kong, Kezhi Zhang, Jiani Shen, Zhengyuan Srinivasan, Balasubramaniam Lei, Chuan Faloutsos, Christos Rangwala, Huzefa Karypis, George |
| contents | Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use a retriever that fetches relevant information to expand LLM's knowledge scope. However, existing textual-oriented retrieval-based LLMs are not ideal on structured table data due to diversified data modalities and large table sizes. In this work, we propose OpenTab, an open-domain table reasoning framework powered by LLMs. Overall, OpenTab leverages table retriever to fetch relevant tables and then generates SQL programs to parse the retrieved tables efficiently. Utilizing the intermediate data derived from the SQL executions, it conducts grounded inference to produce accurate response. Extensive experimental evaluation shows that OpenTab significantly outperforms baselines in both open- and closed-domain settings, achieving up to 21.5% higher accuracy. We further run ablation studies to validate the efficacy of our proposed designs of the system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14361 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OpenTab: Advancing Large Language Models as Open-domain Table Reasoners Kong, Kezhi Zhang, Jiani Shen, Zhengyuan Srinivasan, Balasubramaniam Lei, Chuan Faloutsos, Christos Rangwala, Huzefa Karypis, George Machine Learning Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use a retriever that fetches relevant information to expand LLM's knowledge scope. However, existing textual-oriented retrieval-based LLMs are not ideal on structured table data due to diversified data modalities and large table sizes. In this work, we propose OpenTab, an open-domain table reasoning framework powered by LLMs. Overall, OpenTab leverages table retriever to fetch relevant tables and then generates SQL programs to parse the retrieved tables efficiently. Utilizing the intermediate data derived from the SQL executions, it conducts grounded inference to produce accurate response. Extensive experimental evaluation shows that OpenTab significantly outperforms baselines in both open- and closed-domain settings, achieving up to 21.5% higher accuracy. We further run ablation studies to validate the efficacy of our proposed designs of the system. |
| title | OpenTab: Advancing Large Language Models as Open-domain Table Reasoners |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.14361 |