Common errors in Generative AI systems used for knowledge extraction in the climate action domain

2024/02/01 by Denis Havlik, Havlik, Denis, Marcelo Pias +1
Computer Science · Engineering · #AI-based Problem Solving and Planning #Reservoir Engineering and Simulation Methods #Data Mining Algorithms and Applications

paper · pdf · doi:10.48550/arxiv.2402.00830

Abstract

Large Language Models (LLMs) and, more specifically, the Generative Pre-Trained Transformers (GPT) can help stakeholders in climate action explore digital knowledge bases and extract and utilize climate action knowledge in a sustainable manner. However, LLMs are "probabilistic models of knowledge bases" that excel at generating convincing texts but cannot be entirely relied upon due to the probabilistic nature of the information produced. This brief report illustrates the problem space with examples of LLM responses to some of the questions of relevance to climate action.

Related

• Assessing Large Language Models on Climate Information
• Enhancing Large Language Models with Climate Resources
• Large language models in climate and sustainability policy: limits and opportunities
• Enhancing LLMs for Governance with Human Oversight: Evaluating and Aligning LLMs on Expert Classification of Climate Misinformation for Detecting False or Misleading Claims about Climate Change
• ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change