Jul 2026
Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning?
CreditCardQA, the first financial literacy benchmark for numerical reasoning derived from real credit card agreements, is introduced and error analysis shows that failures arise less from arithmetic and more from misapplied financial rules, missed conditions, and misunderstandings of contractual terms.
Arnav Hiray, Agam Shah, Caleb Lu et al.
· arXiv.org · 0 citations