arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.19346cs.CL
收藏

大型语言模型在数学问题的不合理性上表现挣扎

Large Language Models Struggle with Unreasonability in Math Problems

National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University(国家多媒体信息处理重点实验室,计算机学院,北京大学);Institute of Artificial Intelligence, Beihang University(人工智能学院,北航);Huawei Noah’s Ark Lab, China(华为诺亚实验室,中国)

Jingyuan Ma, Damai Dai, Zihang Yuan, Rui li, Weilin Luo, Bin Wang, Qun Liu, Lei Sha, Zhifang Sui

AI总结:

提出UMP基准评估大型语言模型检测不合理数学问题的能力,实验发现GPT-4o等先进模型表现不佳,推理模型易产生冗长回复,提示和微调方法仅能带来部分改进。

摘要:

大型语言模型(LLMs)在广泛的数学和推理基准测试中展现了显著的成功。然而,我们观察到它们在面对不合理的数学问题时常常表现挣扎。模型未能识别这些问题,而是频繁地继续求解,仿佛问题是适定的,从而产生错误答案或陷入过度思考和冗长的自我纠正。为了系统地研究这一被忽视的脆弱性,我们提出了Unreasonable Math Problems(UMP)基准,旨在评估LLMs检测并应对不合理数学问题陈述的能力。基于涵盖19个LLMs的广泛实验,我们发现,即使是像GPT-4o这样最先进的通用模型在UMP上也仅获得0.6分。虽然像DeepSeek-R1这样的推理模型对不合理输入表现出更高的敏感度,但这通常以生成过于冗长且无意义、无法收敛的回复为代价。我们进一步探索了提示和微调方法,这些方法提供了部分改进,但也引入了权衡,揭示了LLMs在这一具有挑战性的环境中的潜力和局限性。

英文摘要:

Large Language Models (LLMs) have shown remarkable success on a wide range of math and reasoning benchmarks. However, we observe that they often struggle when faced with unreasonable math problems. Instead of recognizing these issues, models frequently proceed as if the problem is well-posed, producing incorrect answers or falling into overthinking and verbose self-correction. To systematically investigate this overlooked vulnerability, we propose the \textbf{Unreasonable Math Problems (UMP)} benchmark, designed to evaluate LLMs' ability to detect and respond to unreasonable math problem statements. Based on extensive experiments covering 19 LLMs, we find that even state-of-the-art general models like GPT-4o achieve only a score of 0.6 on UMP. While reasoning models such as DeepSeek-R1 demonstrate a higher sensitivity to unreasonable inputs, this often comes at the cost of generating overly long and meaningless responses that fail to converge. We further explore prompting and fine-tuning methods, which offer partial improvements but also introduce trade-offs, shedding light on both the potential and limitations of LLMs in this challenging setting.

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。

↑