Towards Automated Scoping of AI for Social Good Projects
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 28 Apr 2025.
Builds on
20 of 28 references.
References · 20
- 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
- 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
- 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
- 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 686
- 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
- 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 291
- 2024DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Datacited by 234
- 2024Large Language Models are Inconsistent and Biased Evaluatorscited by 153
- 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Taskscited by 140
- 2021Proof Artifact Co-training for Theorem Proving with Language Modelscited by 132
- 2023Large Language Models for Automated Open-domain Scientific Hypotheses Discoverycited by 100
- 2022Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Proverscited by 98
8 more
- 2024BLADE: Benchmarking Language Model Agents for Data-Driven Sciencecited by 77
- 2024MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agentscited by 67
- 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 53
- 2024IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedbackcited by 42
- 2024Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluationcited by 41
- 2020Artificial Intelligence for Social Good: A Surveycited by 29
- 2024Conversational Agents as Catalysts for Critical Thinking: Challenging Design Fixation in Group Designcited by 4
- 2024Can Language Models Explain Their Own Classification Behavior?cited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.