We introduce KnowledgeFMath, a novel benchmark designed to evaluate LLMs’ capabilities in solving knowledge-intensive math reasoning problems. Compared to prior works, this study features three core advancements. First, KnowledgeFMath includes 1,259 problems with a hybrid of textual and tabular content. These problems require college-level knowledge in the finance domain for effective resolution. Second, we provide expert-annotated, detailed solution references in Python program format, ensuring a high-quality benchmark for LLM assessment. We also construct a finance-domain knowledge bank and investigate various knowledge integration strategies. Finally, we evaluate a wide spectrum of 26 LLMs with different prompting strategies like Chain-of-Thought and Program-of-Thought. Our experimental results reveal that the current best-performing system (i.e., GPT-4 with CoT prompting) achieves only 56.6% accuracy, leaving substantial room for improvement. Moreover, while augmenting LLMs with external knowledge can improve their performance (e.g., from 33.5% to 47.1% for GPT-3.5), their accuracy remains significantly lower than the estimated human expert performance of 92%. We believe that KnowledgeFMath can advance future research in the area of domain-specific knowledge retrieval and integration, particularly within the context of solving math reasoning problems.

Recent LLMs have demonstrated remarkable performance in solving exam-like math word problems. However, the degree to which these numerical reasoning skills are effective in real-world scenarios, particularly in expert domains, is still largely unexplored. This paper introduces DocMath-Eval, a comprehensive benchmark specifically designed to evaluate the numerical reasoning capabilities of LLMs in the context of understanding and analyzing financial documents containing both text and tables. We evaluate a wide spectrum of 27 LLMs, including those specialized in math, coding and finance, with Chain-of-Thought and Program-of-Thought prompting methods. We found that even the current best-performing system (i.e., GPT-4) still significantly lags behind human experts in solving complex numerical reasoning problems grounded in long contexts. We believe DocMath-Eval can be used as a valuable benchmark to evaluate LLMs’ capabilities to solve challenging numerical reasoning problems in expert domains.