Towards Automated Scoping of AI for Social Good Projects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Emmerson, Jacob, Ghani, Rayid, Shi, Zheyuan Ryan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912350975557632
author Emmerson, Jacob
Ghani, Rayid
Shi, Zheyuan Ryan
author_facet Emmerson, Jacob
Ghani, Rayid
Shi, Zheyuan Ryan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20010
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Automated Scoping of AI for Social Good Projects
Emmerson, Jacob
Ghani, Rayid
Shi, Zheyuan Ryan
Artificial Intelligence
Computers and Society
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.
title Towards Automated Scoping of AI for Social Good Projects
topic Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2504.20010