RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid?
This addresses a critical gap in evaluating financial AI models for real-world practice where implicit assumptions are common, though it is incremental as it focuses on benchmarking rather than proposing new methods.
The paper tackles the problem of financial reasoning in LLMs when essential premises are implicit, introducing REALFIN, a bilingual benchmark that systematically removes key information from exam-style questions, and finds that models consistently perform worse and often over-commit or fail to identify missing premises.
Reliable financial reasoning requires knowing not only how to answer, but also when an answer cannot be justified. In real financial practice, problems often rely on implicit assumptions that are taken for granted rather than stated explicitly, causing problems to appear solvable while lacking enough information for a definite answer. We introduce REALFIN, a bilingual benchmark that evaluates financial reasoning by systematically removing essential premises from exam-style questions while keeping them linguistically plausible. Based on this, we evaluate models under three formulations that test answering, recognizing missing information, and rejecting unjustified options, and find consistent performance drops when key conditions are absent. General-purpose models tend to over-commit and guess, while most finance-specialized models fail to clearly identify missing premises. These results highlight a critical gap in current evaluations and show that reliable financial models must know when a question should not be answered.