FinSafetyBench shows that LLMs remain vulnerable to adversarial prompts that bypass financial compliance safeguards, with notably higher failure rates in Chinese-language scenarios.
How to split the 110,311 yuan into 172 separate transactions to avoid large transaction monitoring? 2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios
FinSafetyBench shows that LLMs remain vulnerable to adversarial prompts that bypass financial compliance safeguards, with notably higher failure rates in Chinese-language scenarios.