GLoRE: Evaluating Logical Reasoning of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: liu, Hanmeng, Teng, Zhiyang, Ning, Ruoxi, Ding, Yiran, Li, Xiulai, Liu, Xiaozhang, Zhang, Yue
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908327049428992
author liu, Hanmeng
Teng, Zhiyang
Ning, Ruoxi
Ding, Yiran
Li, Xiulai
Liu, Xiaozhang
Zhang, Yue
author_facet liu, Hanmeng
Teng, Zhiyang
Ning, Ruoxi
Ding, Yiran
Li, Xiulai
Liu, Xiaozhang
Zhang, Yue
contents Large language models (LLMs) have shown significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language understanding. To encourage further investigation in this area, we introduce GLoRE, a General Logical Reasoning Evaluation platform that not only consolidates diverse datasets but also standardizes them into a unified format suitable for evaluating large language models across zero-shot and few-shot scenarios. Our experimental results show that compared to the performance of humans and supervised fine-tuning models, the logical reasoning capabilities of large reasoning models, such as OpenAI's o1 mini, DeepSeek R1 and QwQ-32B, have seen remarkable improvements, with QwQ-32B achieving the highest benchmark performance to date. GLoRE is designed as a living project that continuously integrates new datasets and models, facilitating robust and comparative assessments of model performance in both commercial and Huggingface communities.
format Preprint
id arxiv_https___arxiv_org_abs_2310_09107
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GLoRE: Evaluating Logical Reasoning of Large Language Models
liu, Hanmeng
Teng, Zhiyang
Ning, Ruoxi
Ding, Yiran
Li, Xiulai
Liu, Xiaozhang
Zhang, Yue
Computation and Language
Artificial Intelligence
Large language models (LLMs) have shown significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language understanding. To encourage further investigation in this area, we introduce GLoRE, a General Logical Reasoning Evaluation platform that not only consolidates diverse datasets but also standardizes them into a unified format suitable for evaluating large language models across zero-shot and few-shot scenarios. Our experimental results show that compared to the performance of humans and supervised fine-tuning models, the logical reasoning capabilities of large reasoning models, such as OpenAI's o1 mini, DeepSeek R1 and QwQ-32B, have seen remarkable improvements, with QwQ-32B achieving the highest benchmark performance to date. GLoRE is designed as a living project that continuously integrates new datasets and models, facilitating robust and comparative assessments of model performance in both commercial and Huggingface communities.
title GLoRE: Evaluating Logical Reasoning of Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2310.09107