用AI自动起草内容安全政策，省去人工成本。
Open-Domain Safety Policy Construction
- 基于人类种子信息，通过搜索与归纳生成政策规则。
- 在5个领域上优于纯定义和上下文学习基线。
- 适合需要快速构建安全策略的团队或平台使用。
内容审核层正成为用户或模型生成内容产品的重要组成部分。然而，制定和维护特定领域的安全政策成本高昂。我们提出Deep Policy Research（DPR），一个极简代理系统，仅需人类编写的种子领域信息即可自动生成完整的内容审核政策。DPR利用单一网络搜索工具和轻量级框架，迭代生成搜索查询，从多样网页来源中提炼出政策规则，并组织成索引文档。我们在（1）OpenAI五个领域的不良内容基准测试中，使用两个小型阅读型LLM进行评估；（2）内部多模态广告审核基准测试。结果表明，DPR始终优于仅依赖定义和上下文学习的基线，在端到端设置下与专家撰写的政策部分在多个领域表现相当。此外，在相同种子信息和评估协议下，DPR优于通用深度研究系统，说明任务特化、结构化的研究循环比通用网络研究更适用于政策起草。代码已开源：https://github.com/xiaowu0162/deep-policy-research。
原文摘要 · Abstract (English)
Moderation layers are increasingly a core component of many products built on user- or model-generated content. However, drafting and maintaining domain-specific safety policies remains costly. We present Deep Policy Research (DPR), a minimal agentic system that drafts a full content moderation policy based on only human-written seed domain information. DPR uses a single web search tool and lightweight scaffolding to iteratively propose search queries, distill diverse web sources into policy rules, and organize rules into an indexed document. We evaluate DPR on (1) the OpenAI undesired content benchmark across five domains with two compact reader LLMs and (2) an in-house multimodal advertisement moderation benchmark. DPR consistently outperforms definition-only and in-context learning baselines, and in our end-to-end setting it is competitive with expert-written policy sections in several domains. Moreover, under the same seed specification and evaluation protocol, DPR outperforms a general-purpose deep research system, suggesting that a task-specific, structured research loop can be more effective than generic web research for policy drafting. We release our experiment code at https://github.com/xiaowu0162/deep-policy-research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。