2024/03/28 by Jingyuan Ma, Damai Dai, Ma, Jingyuan +8 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2403.19346
openalex publication_date 2024/03/28 · openalex created_date 2024/03/30 · openalex updated_date 2026/07/28
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 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.