用大模型自动生成社会向AI项目方案，省去专家人力
Towards Automated Scoping of AI for Social Good Projects
- 用大语言模型自动生成基于科学文献的社会问题解决方案
- 盲评显示生成方案与专家撰写水平相当
- 适合缺乏跨领域专家的公益科技团队快速启动项目
人工智能赋能社会福祉（AI4SG）致力于利用AI的强大能力应对复杂社会挑战，从本地交通网络到全球野生动物保护。然而，无论规模大小，许多AI4SG项目面临的关键瓶颈是问题定义过程——这一需要大量人力且资源密集的任务，源于兼具技术与领域知识的专业人才稀缺。鉴于大语言模型（LLM）的显著应用潜力，我们提出问题定义代理（Problem Scoping Agent, PSA），利用LLM生成基于科学文献和现实知识的完整项目提案。通过盲审和AI评估，我们证明了PSA框架生成的提案在质量上可媲美专家撰写。最后，我们记录了真实世界问题定义中的挑战，并指出了未来工作的几个方向。
原文摘要 · Abstract (English)
Artificial Intelligence for Social Good (AI4SG) is an emerging effort that aims to address complex societal challenges with the powerful capabilities of AI systems. These challenges range from local issues with transit networks to global wildlife preservation. However, regardless of scale, a critical bottleneck for many AI4SG initiatives is the laborious process of problem scoping -- a complex and resource-intensive task -- due to a scarcity of professionals with both technical and domain expertise. Given the remarkable applications of large language models (LLM), we propose a Problem Scoping Agent (PSA) that uses an LLM to generate comprehensive project proposals grounded in scientific literature and real-world knowledge. We demonstrate that our PSA framework generates proposals comparable to those written by experts through a blind review and AI evaluations. Finally, we document the challenges of real-world problem scoping and note several areas for future work.
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。