Publication
LLMs-Assisted decision-making in sustainable contexts
| Summary: | Promoting sustainability through creative approaches offers a path way to achieving sustainability goals, yet the resulting solutions often lack efficiency and effectiveness. Addressing this challenge, we introduce SAIESE, a Creativity Support Tool (CST) leveraging a Large Language Model (LLM) to support the creative process, the generation, evaluation, and selection of sustainable ideas. Our work articulates LLMs role in exploration and selection, focusing on sustainable ideas based on three metrics- Environmental Impact, Economic Benefits, and Social Effects. Our evaluation demonstrates that the prototype outperforms human evaluative tasks in usability, creative thinking, and decision-making while reducing cognitive workload. However, its effectiveness in promoting creativity de pends on the clarity of ideas, underlining the importance of hu man collaboration in ambiguous contexts. This work articulates the potential of AI in creativity, expanding current research on CSTs by highlighting sustainability-oriented creative processes and decision-making support. |
|---|---|
| Main Authors: | Rodrigues, Ana |
| Other Authors: | Cabral, Diogo; Campos, Pedro; Rodrigues, Ana Isabel; Pereira Campos, Pedro Filipe; Campos, Pedro |
| Subject: | Creative process Creativity support tool LLMs Sustainability . Faculdade de Ciências Exatas e da Engenharia |
| Year: | 2025 |
| Country: | Portugal |
| Document type: | conference paper |
| Access type: | open access |
| Associated institution: | Universidade da Madeira |
| Language: | English |
| Origin: | DigitUMa - Repositório da Universidade da Madeira |
| Summary: | Promoting sustainability through creative approaches offers a path way to achieving sustainability goals, yet the resulting solutions often lack efficiency and effectiveness. Addressing this challenge, we introduce SAIESE, a Creativity Support Tool (CST) leveraging a Large Language Model (LLM) to support the creative process, the generation, evaluation, and selection of sustainable ideas. Our work articulates LLMs role in exploration and selection, focusing on sustainable ideas based on three metrics- Environmental Impact, Economic Benefits, and Social Effects. Our evaluation demonstrates that the prototype outperforms human evaluative tasks in usability, creative thinking, and decision-making while reducing cognitive workload. However, its effectiveness in promoting creativity de pends on the clarity of ideas, underlining the importance of hu man collaboration in ambiguous contexts. This work articulates the potential of AI in creativity, expanding current research on CSTs by highlighting sustainability-oriented creative processes and decision-making support. |
|---|