Are Large Language Models Table-based Fact-Checkers?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Hanwen, Si, Qingyi, Fu, Peng, Lin, Zheng, Wang, Weiping
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929589356331008
author Zhang, Hanwen
Si, Qingyi
Fu, Peng
Lin, Zheng
Wang, Weiping
author_facet Zhang, Hanwen
Si, Qingyi
Fu, Peng
Lin, Zheng
Wang, Weiping
contents Table-based Fact Verification (TFV) aims to extract the entailment relation between statements and structured tables. Existing TFV methods based on small-scaled models suffer from insufficient labeled data and weak zero-shot ability. Recently, the appearance of Large Language Models (LLMs) has gained lots of attraction in research fields. They have shown powerful zero-shot and in-context learning abilities on several NLP tasks, but their potential on TFV is still unknown. In this work, we implement a preliminary study about whether LLMs are table-based fact-checkers. In detail, we design diverse prompts to explore how the in-context learning can help LLMs in TFV, i.e., zero-shot and few-shot TFV capability. Besides, we carefully design and construct TFV instructions to study the performance gain brought by the instruction tuning of LLMs. Experimental results demonstrate that LLMs can achieve acceptable results on zero-shot and few-shot TFV with prompt engineering, while instruction-tuning can stimulate the TFV capability significantly. We also make some valuable findings about the format of zero-shot prompts and the number of in-context examples. Finally, we analyze some possible directions to promote the accuracy of TFV via LLMs, which is beneficial to further research of table reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Are Large Language Models Table-based Fact-Checkers?
Zhang, Hanwen
Si, Qingyi
Fu, Peng
Lin, Zheng
Wang, Weiping
Computation and Language
Artificial Intelligence
Machine Learning
Table-based Fact Verification (TFV) aims to extract the entailment relation between statements and structured tables. Existing TFV methods based on small-scaled models suffer from insufficient labeled data and weak zero-shot ability. Recently, the appearance of Large Language Models (LLMs) has gained lots of attraction in research fields. They have shown powerful zero-shot and in-context learning abilities on several NLP tasks, but their potential on TFV is still unknown. In this work, we implement a preliminary study about whether LLMs are table-based fact-checkers. In detail, we design diverse prompts to explore how the in-context learning can help LLMs in TFV, i.e., zero-shot and few-shot TFV capability. Besides, we carefully design and construct TFV instructions to study the performance gain brought by the instruction tuning of LLMs. Experimental results demonstrate that LLMs can achieve acceptable results on zero-shot and few-shot TFV with prompt engineering, while instruction-tuning can stimulate the TFV capability significantly. We also make some valuable findings about the format of zero-shot prompts and the number of in-context examples. Finally, we analyze some possible directions to promote the accuracy of TFV via LLMs, which is beneficial to further research of table reasoning.
title Are Large Language Models Table-based Fact-Checkers?
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.02549