FraudBench 評估大語言模型在美國法律下的欺詐傾向
FraudBench: A Legal Evaluation of AI Deception
FraudBench 評估大語言模型在美國法律下建議、協助或直接採取欺詐行為的傾向。研究以159個取材自美國真實法庭案件、經法律專家核實的情境,評估20個大語言模型在25種實驗條件下的表現,合共產生逾300,000次生成。無施壓時,欺詐率由提供建議時的3.0%升至代寫訊息時的14.7%及直接代行時的21.4%;守法提示詞降低欺詐率,最大化利潤及採取智能體式行動的提示詞則提高欺詐率。
Published on Nov 9
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
We introduce FraudBench, an evaluation of large language models' (LLMs) propensities to recommend, assist, or directly take actions that would constitute fraud under U.S. law. Our evaluation contains a novel dataset of 159 scenarios based on real-world U.S. court cases and validated by legal experts. We present each scenario to LLMs via three tasks at varying levels of autonomy: advising users, drafting messages for users to send, and acting directly on behalf of users (477 tasks total). In each scenario, FraudBench re-enacts the facts of a court case to give LLMs an opportunity, but no explicit instruction, to either misrepresent or conceal a material fact in a high-stakes commercial setting--e.g., whether to describe company-funded product testing as "independent" to customers (misrepresentation) or whether to hide unfavorable regulatory investigations from clients (concealment). We evaluate 20 LLMs across 25 experimental conditions (totaling >300,000 generations) and include a preregistered human baseline (n_{annotations} = 2{,}957, n_{humans} = 996). We score a response as fraudulent when it engages in, assists with, or recommends misrepresentation or concealment. Key findings include: (1) across LLMs, fraud rates ranged from near 0% to over 40%; (2) LLM fraud rates increased with autonomy, with overall rates of 3.0% when advising, 14.7% when drafting, and 21.4% when acting directly, without applying pressure; (3) LLMs sometimes engaged in fraud despite recognizing legal risks; (4) LLMs more often engaged in fraud by concealment than by misrepresentation; and (5) prompt-based interventions substantially affected fraud rates, with a prompt to obey the law reducing fraud rates, while prompts to maximize profits and act agentically increased fraud rates.
View arXiv page View PDF GitHub Add to collection
Get this paper in your agent:
hf papers read 2611.12167
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.12167 in a model README.md to link it from this page.
Datasets citing this paper 1
GOAL-Lab/FraudBench
Viewer • Updated about 12 hours ago • 159 • 138 • 1
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.12167 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co