arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.09613cs.CLcs.AI
收藏

基于Transformer的语言模型在描述逻辑ALCQ中的推理

Transformer-based Language Models for Reasoning in the Description Logic ALCQ

National and Kapodistrian University of Athens(雅典国立卡波迪斯特里亚大学);Boston University(波士顿大学);Athens Technology Center(雅典技术中心);Archimedes/Athena RC(阿基米德/雅典娜研究中心)

Angelos Poulis, Eleni Tsalapati, Manolis Koubarakis

AI总结:

本文使用描述逻辑ALCQ构建了自然语言数据集DELTA_D,系统评估了DeBERTa和GPT模型的逻辑推理能力,发现微调后的DeBERTa能掌握蕴含检查任务,且少样本提示能显著提升GPT性能。

摘要:

基于Transformer的语言模型的最新进展引发了对它们逻辑推理能力的研究。大多数用于评估这些模型的基准都很简单:由仅包含少量逻辑算子和量词的短(片段)一阶逻辑句子生成。我们使用富有表达力的描述逻辑语言$\mathcal{ALCQ}$构建了自然语言数据集DELTA$_D$。DELTA$_D$包含384K个样本,并在两个维度上有所增加:i) 推理深度,和 ii) 语言复杂度。通过这种方式,我们系统地研究了一个监督微调的基于DeBERTa的模型和两个大语言模型(GPT-3.5、GPT-4)在少样本提示下的逻辑推理能力。我们展示了在我们的数据集上微调的基于DeBERTa的模型能够掌握蕴含检查任务。此外,即使仅提供少量样本(9 shots),GPT的性能也能显著提升。我们开源了我们的代码和数据集。

英文摘要:

Recent advancements in transformer-based language models have sparked research into their logical reasoning capabilities. Most of the benchmarks used to evaluate these models are simple: generated from short (fragments of) first-order logic sentences with only a few logical operators and quantifiers. We construct the natural language dataset, DELTA$_D$, using the expressive description logic language $\mathcal{ALCQ}$. DELTA$_D$ comprises 384K examples and increases in two dimensions: i) reasoning depth, and ii) linguistic complexity. In this way, we systematically investigate the logical reasoning capabilities of a supervised fine-tuned DeBERTa-based model and two large language models (GPT-3.5, GPT-4) with few-shot prompting. We show that the DeBERTa-based model fine-tuned on our dataset can master the entailment checking task. Moreover, the performance of GPTs can improve significantly even when a small number of samples is provided (9 shots). We open-source our code and datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑