A Dataset for Detecting Real-World Environmental Claims

Stammbach, Dominik; Webersinke, Nicolas; Bingler, Julia; Kraus, Mathias; Leippold, Markus

doi:10.2139/ssrn.4207369

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…35,36 ). To this extent, we are building an authoritative and accurate knowledge base that can be used to fact-check domain-specific claims 39 or LLM-produced responses.…”

Section: Chatclimate Hybrid Prompt-1mentioning

confidence: 99%

ChatClimate: Grounding conversational AI in climate science

Vaghefi,

Stammbach,

Muccione

et al. 2023

Commun Earth Environ

View full text Add to dashboard Cite

Large Language Models have made remarkable progress in question-answering tasks, but challenges like hallucination and outdated information persist. These issues are especially critical in domains like climate change, where timely access to reliable information is vital. One solution is granting these models access to external, scientifically accurate sources to enhance their knowledge and reliability. Here, we enhance GPT-4 by providing access to the Sixth Assessment Report of the Intergovernmental Panel on Climate Change (IPCC AR6), the most comprehensive, up-to-date, and reliable source in this domain (refer to the ’Data Availability’ section). We present our conversational AI prototype, available at www.chatclimate.ai, and demonstrate its ability to answer challenging questions in three different setups: (1) GPT-4, (2) ChatClimate, which relies exclusively on IPCC AR6 reports, and (3) Hybrid ChatClimate, which utilizes IPCC AR6 reports with in-house GPT-4 knowledge. The evaluation of answers by experts show that the hybrid ChatClimate AI assistant provide more accurate responses, highlighting the effectiveness of our solution.

show abstract

“…35,36 ). To this extent, we are building an authoritative and accurate knowledge base that can be used to fact-check domain-specific claims 39 or LLM-produced responses.…”

Section: Chatclimate Hybrid Prompt-1mentioning

confidence: 99%

ChatClimate: Grounding conversational AI in climate science

Vaghefi,

Stammbach,

Muccione

et al. 2023

Commun Earth Environ

View full text Add to dashboard Cite

show abstract

Environmental Sustainability of Family Firms: A Meta-Analysis of Handprint and Footprint

Lorenzen,

Gerken,

Steinmetz

et al. 2024

Entrepreneurship Theory and Practice

View full text Add to dashboard Cite

Our meta-analysis investigates the environmental sustainability performance of family firms (FFs) distinguishing between environmental hand- and footprint and accounting for FF heterogeneity. Based on a sample of 87 primary studies comprising 118,538 firms, we find no significant difference between FFs and non-FFs regarding their overall environmental sustainability performance. Yet, distinguishing between environmental hand- and footprint, we show that FFs have a lower footprint than non-FFs but do not differ regarding their handprint. Firm size, being a public firm, and type of family involvement moderate the effects of FF status on environmental sustainability performance. Our research note extends prior meta-analytical evidence and contributes to a more fine-grained and nuanced understanding of the environmental sustainability performance of FFs. Theoretical and managerial implications are discussed.

show abstract

A Dataset for Detecting Real-World Environmental Claims

Cited by 2 publications

References 13 publications

ChatClimate: Grounding conversational AI in climate science

ChatClimate: Grounding conversational AI in climate science

Environmental Sustainability of Family Firms: A Meta-Analysis of Handprint and Footprint

Contact Info

Product

Resources

About