English

CLR-Bench: Evaluating Large Language Models in College-level Reasoning

Artificial Intelligence 2024-10-28 v2

Abstract

Large language models (LLMs) have demonstrated their remarkable performance across various language understanding tasks. While emerging benchmarks have been proposed to evaluate LLMs in various domains such as mathematics and computer science, they merely measure the accuracy in terms of the final prediction on multi-choice questions. However, it remains insufficient to verify the essential understanding of LLMs given a chosen choice. To fill this gap, we present CLR-Bench to comprehensively evaluate the LLMs in complex college-level reasoning. Specifically, (i) we prioritize 16 challenging college disciplines in computer science and artificial intelligence. The dataset contains 5 types of questions, while each question is associated with detailed explanations from experts. (ii) To quantify a fair evaluation of LLMs' reasoning ability, we formalize the criteria with two novel metrics. Q\rightarrowA is utilized to measure the performance of direct answer prediction, and Q\rightarrowAR effectively considers the joint ability to answer the question and provide rationale simultaneously. Extensive experiments are conducted with 40 LLMs over 1,018 discipline-specific questions. The results demonstrate the key insights that LLMs, even the best closed-source LLM, i.e., GPT-4 turbo, tend to `guess' the college-level answers. It shows a dramatic decrease in accuracy from 63.31% Q\rightarrowA to 39.00% Q\rightarrowAR, indicating an unsatisfactory reasoning ability.

Keywords

Cite

@article{arxiv.2410.17558,
  title  = {CLR-Bench: Evaluating Large Language Models in College-level Reasoning},
  author = {Junnan Dong and Zijin Hong and Yuanchen Bei and Feiran Huang and Xinrun Wang and Xiao Huang},
  journal= {arXiv preprint arXiv:2410.17558},
  year   = {2024}
}

Comments

18 pages, 6 figures, dataset and evaluation framework will be opensourced

R2 v1 2026-06-28T19:32:24.697Z