Large language models (LLMs) have significantly transformed the landscape of artificial intelligence by demonstrating their ability to generate human-like text across diverse topics. However, despite their impressive capabilities, LLMs lack recent information and 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, including databases containing recent and precise information about organizations, institutions, and companies. We demonstrate the effectiveness of our method through a prototype agent that retrieves emission data from ClimateWatch (https://www.climatewatchdata.org/) and leverages general Google search. By integrating these resources with LLMs, our approach overcomes the limitations associated with imprecise language and delivers more reliable and accurate information in the critical domain of climate change. This work paves the way for future advancements in LLMs and their application in domains where precision is of paramount importance.
Large Language Models (LLMs) have made significant progress in recent years, achieving remarkable results in question-answering tasks (QA). However, they still face two major challenges: hallucination and outdated information after the training phase. These challenges take center stage in critical domains like climate change, where obtaining accurate and up-to-date information from reliable sources in a limited time is essential and difficult. To overcome these barriers, one potential solution is to provide LLMs with access to external, scientifically accurate, and robust sources (long-term memory) to continuously update their knowledge and prevent the propagation of inaccurate, incorrect, or outdated information. In this study, we enhanced GPT-4 by integrating the information from the Sixth Assessment Report of the Intergovernmental (IPCC AR6), the most comprehensive, up-to-date, and reliable source in this domain. We present our conversational AI prototype, available at www.chatclimate.ai, for his invaluable and voluntary support in setting up the server. The server will become available by mid-April.} and demonstrate its ability to answer challenging questions accurately. The answers and their sources were evaluated by our team of IPCC authors, who used their expert knowledge to score the accuracy of the answers from 1 (very-low) to 5 (very-high). The evaluation showed that the hybrid chatClimate provided more accurate answers, highlighting the effectiveness of our solution. This approach can be easily scaled for chatbots in specific domains, enabling the delivery of reliable and accurate information.
Public and private actors struggle to assess the vast amounts of information about sustainability commitments made by various institutions. To address this problem, we create a novel tool for automatically detecting corporate, national, and regional net zero and reduction targets in three steps. First, we introduce an expert-annotated data set with 3.5K text samples. Second, we train and release ClimateBERT-NetZero, a natural language classifier to detect whether a text contains a net zero or reduction target. Third, we showcase its analysis potential with two use cases: We first demonstrate how ClimateBERT-NetZero can be combined with conventional question-answering (Q&A) models to analyze the ambitions displayed in net zero and reduction targets. Furthermore, we employ the ClimateBERT-NetZero model on quarterly earning call transcripts and outline how communication patterns evolve over time. Our experiments demonstrate promising pathways for extracting and analyzing net zero and emission reduction targets at scale.
Companies need sound planning to reduce their emissions and deal with the transition to a more sustainable economy. The disclosure of such plans is key for effective capital allocation and risk management. Transition and sustainability disclosures are a compass for market participants to guide their actions and strategies toward the net-zero target. If companies plan their transition appropriately, the negative implications of physical and transition risks for micro- and macro-financial stability can be reduced. Many frameworks have been suggested to assess transition plans’ ambition, credibility, and feasibility. However, the lack of one clear reference framework paves the way for inconsistencies in transition plans and the risk of greenwashing. We propose a set of 64 common ground indicators from 28 different transition plan disclosure frameworks to comprehensively assess transition plans and develop a novel natural language processing (NLP)–based tool to automate the assessment of companies’ disclosures. This can help investors and financial supervisors assess transition risks while supporting companies’ disclosure efforts. Applying the tool to 143 reports from the carbon-intensive CA100+ companies, we find that companies tend to disclose more indicators related to target setting (talk) but fewer indicators related to the concrete implementation of strategies (walk). Our results demonstrate that machine learning can be used to generate a positive impact on the transition towards a more sustainable economy by identifying the elements of transition plans that require further scrutiny and/or effort. Our work will be a starting point for further leveraging new technologies in sustainable finance. For example, the assessment of the plans could be used by financial regulators in their supervisory practices or to investigate whether the risk of greenwashing is reflected in stock returns.
Nature is an amorphous concept. Yet, it is essential for the planet's well-being to understand how the economy interacts with it. To address the growing demand for information on corporate nature disclosure, we provide datasets and classifiers to detect nature communication by companies. We ground our approach in the guidelines of the Taskforce on Nature-related Financial Disclosures (TNFD). Particularly, we focus on the specific dimensions of water, forest, and biodiversity. For each dimension, we create an expert-annotated dataset with 2,200 text samples and train classifier models. Furthermore, we show that nature communication is more prevalent in hotspot areas and directly effected industries like agriculture and utilities. Our approach is the first to respond to calls to assess corporate nature communication on a large scale.