FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918477419249664 |
|---|---|
| author | Hou, Yutao Jiang, Yihan Xie, Yuhan Yang, Jian Zhang, Liwen Huang, Hailiang Chen, Guanhua Chen, Yun |
| author_facet | Hou, Yutao Jiang, Yihan Xie, Yuhan Yang, Jian Zhang, Liwen Huang, Hailiang Chen, Guanhua Chen, Yun |
| contents | Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically evaluate LLM safety in finance, we propose FinSafetyBench, a bilingual (English-Chinese) red-teaming benchmark designed to test an LLM's refusal of requests that violate financial compliance. Grounded in real-world financial crime cases and ethics standards, the benchmark comprises 14 subcategories spanning financial crimes and ethical violations. Through extensive experiments on general-purpose and finance-specialized LLMs under three representative attack settings, we identify critical vulnerabilities that allow adversarial prompts to bypass compliance safeguards. Further analysis reveals stronger susceptibility in Chinese contexts and highlights the limitations of prompt-level defenses against sophisticated or implicit manipulation strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00706 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios Hou, Yutao Jiang, Yihan Xie, Yuhan Yang, Jian Zhang, Liwen Huang, Hailiang Chen, Guanhua Chen, Yun Computation and Language Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically evaluate LLM safety in finance, we propose FinSafetyBench, a bilingual (English-Chinese) red-teaming benchmark designed to test an LLM's refusal of requests that violate financial compliance. Grounded in real-world financial crime cases and ethics standards, the benchmark comprises 14 subcategories spanning financial crimes and ethical violations. Through extensive experiments on general-purpose and finance-specialized LLMs under three representative attack settings, we identify critical vulnerabilities that allow adversarial prompts to bypass compliance safeguards. Further analysis reveals stronger susceptibility in Chinese contexts and highlights the limitations of prompt-level defenses against sophisticated or implicit manipulation strategies. |
| title | FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.00706 |