CNFinBench finds LLMs lose about 15 points from single modules to full agentic execution chains, and their financial-compliance violations surge roughly 160-170% by the second round of multi-turn adversarial attacks.
Title resolution pending
1 Pith paper cite this work, alongside 8 external citations. Polarity classification is still indexing.
1
Pith paper citing it
8
external citations · OpenAlex
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Knowledge to Agency: Evaluating Expertise, Autonomy, and Integrity in Finance with CNFinBench
CNFinBench finds LLMs lose about 15 points from single modules to full agentic execution chains, and their financial-compliance violations surge roughly 160-170% by the second round of multi-turn adversarial attacks.