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

• URL: http://arxiv.org/abs/2402.00830v1
• Date: Thu, 1 Feb 2024 18:17:29 GMT
• Title: Common errors in Generative AI systems used for knowledge extraction in the climate action domain
• Authors: Denis Havlik, Marcelo Pias
• Abstract summary: 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. 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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 papers

• Language Agents Meet Causality -- Bridging LLMs and Causal World Models [50.79984529172807]
  We propose a framework that integrates causal representation learning with large language models. This framework learns a causal world model, with causal variables linked to natural language expressions. We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities.
  arXiv  Detail & Related papers  (2024-10-25T18:36:37Z)
• Unlearning Climate Misinformation in Large Language Models [17.95497650321137]
  Misinformation regarding climate change is a key roadblock in addressing one of the most serious threats to humanity. This paper investigates factual accuracy in large language models (LLMs) regarding climate information.
  arXiv  Detail & Related papers  (2024-05-29T23:11:53Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities. If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information. To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• Quantitative knowledge retrieval from large language models [4.155711233354597]
  Large language models (LLMs) have been extensively studied for their abilities to generate convincing natural language sequences. This paper explores the feasibility of LLMs as a mechanism for quantitative knowledge retrieval to aid data analysis tasks.
  arXiv  Detail & Related papers  (2024-02-12T16:32:37Z)
• Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting [51.7049140329611]
  This paper proposes Knowledge Graph-based Retrofitting (KGR) to mitigate factual hallucination during the reasoning process. Experiments show that KGR can significantly improve the performance of LLMs on factual QA benchmarks.
  arXiv  Detail & Related papers  (2023-11-22T11:08:38Z)
• Are Large Language Models Geospatially Knowledgeable? [21.401931052512595]
  This paper investigates the extent of geospatial knowledge, awareness, and reasoning abilities encoded within Large Language Models (LLM) With a focus on autoregressive language models, we devise experimental approaches related to (i) probing LLMs for geo-coordinates to assess geospatial knowledge, (ii) using geospatial and non-geospatial prepositions to gauge their geospatial awareness, and (iii) utilizing a multidimensional scaling (MDS) experiment to assess the models' geospatial reasoning capabilities.
  arXiv  Detail & Related papers  (2023-10-09T17:20:11Z)
• Thrust: Adaptively Propels Large Language Models with External Knowledge [58.72867916604562]
  Large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters. The inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. We propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary.
  arXiv  Detail & Related papers  (2023-07-19T20:16:46Z)
• On the Risk of Misinformation Pollution with Large Language Models [127.1107824751703]
  We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation in the performance of Open-Domain Question Answering (ODQA) systems.
  arXiv  Detail & Related papers  (2023-05-23T04:10:26Z)
• Enhancing Large Language Models with Climate Resources [5.2677629053588895]
  Large language models (LLMs) have transformed the landscape of artificial intelligence by demonstrating their ability in generating human-like text. However, they often employ imprecise language, which can be detrimental in domains where accuracy is crucial, such as climate change. In this study, we make use of recent ideas to harness the potential of LLMs by viewing them as agents that access multiple sources. We demonstrate the effectiveness of our method through a prototype agent that retrieves emission data from ClimateWatch.
  arXiv  Detail & Related papers  (2023-03-31T20:24:14Z)
• Principled Knowledge Extrapolation with GANs [92.62635018136476]
  We study counterfactual synthesis from a new perspective of knowledge extrapolation. We show that an adversarial game with a closed-form discriminator can be used to address the knowledge extrapolation problem. Our method enjoys both elegant theoretical guarantees and superior performance in many scenarios.
  arXiv  Detail & Related papers  (2022-05-21T08:39:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.