Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Schimanski, Tobias"'
Autor:
Ni, Jingwei, Schimanski, Tobias, Lin, Meihong, Sachan, Mrinmaya, Ash, Elliott, Leippold, Markus
Retrieval Augmented Generation (RAG) is widely employed to ground responses to queries on domain-specific documents. But do RAG implementations leave out important information or excessively include irrelevant information? To allay these concerns, it
Externí odkaz:
http://arxiv.org/abs/2406.14162
To handle the vast amounts of qualitative data produced in corporate climate communication, stakeholders increasingly rely on Retrieval Augmented Generation (RAG) systems. However, a significant gap remains in evaluating domain-specific information r
Externí odkaz:
http://arxiv.org/abs/2406.09818
Advances towards more faithful and traceable answers of Large Language Models (LLMs) are crucial for various research and practical endeavors. One avenue in reaching this goal is basing the answers on reliable sources. However, this Evidence-Based QA
Externí odkaz:
http://arxiv.org/abs/2402.08277
Autor:
Leippold, Markus, Vaghefi, Saeid Ashraf, Stammbach, Dominik, Muccione, Veruska, Bingler, Julia, Ni, Jingwei, Colesanti-Senni, Chiara, Wekhof, Tobias, Schimanski, Tobias, Gostlow, Glen, Yu, Tingyu, Luterbacher, Juerg, Huggel, Christian
This paper presents Climinator, a novel AI-based tool designed to automate the fact-checking of climate change claims. Utilizing an array of Large Language Models (LLMs) informed by authoritative sources like the IPCC reports and peer-reviewed scient
Externí odkaz:
http://arxiv.org/abs/2401.12566
Autor:
Schimanski, Tobias, Senni, Chiara Colesanti, Gostlow, Glen, Ni, Jingwei, Yu, Tingyu, Leippold, Markus
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 det
Externí odkaz:
http://arxiv.org/abs/2312.17337
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
Externí odkaz:
http://arxiv.org/abs/2310.08096
Autor:
Ni, Jingwei, Bingler, Julia, Colesanti-Senni, Chiara, Kraus, Mathias, Gostlow, Glen, Schimanski, Tobias, Stammbach, Dominik, Vaghefi, Saeid Ashraf, Wang, Qian, Webersinke, Nicolas, Wekhof, Tobias, Yu, Tingyu, Leippold, Markus
In the face of climate change, are companies really taking substantial steps toward more sustainable operations? A comprehensive answer lies in the dense, information-rich landscape of corporate sustainability reports. However, the sheer volume and c
Externí odkaz:
http://arxiv.org/abs/2307.15770
Autor:
Ni, Jingwei, Bingler, Julia, Colesanti-Senni, Chiara, Kraus, Mathias, Gostlow, Glen, Schimanski, Tobias, Stammbach, Dominik, Vaghefi, Saeid Ashraf, Wang, Qian, Webersinke, Nicolas, Wekhof, Tobias, Yu, Tingyu, Leippold, Markus
This paper introduces a novel approach to enhance Large Language Models (LLMs) with expert knowledge to automate the analysis of corporate sustainability reports by benchmarking them against the Task Force for Climate-Related Financial Disclosures (T
Externí odkaz:
http://arxiv.org/abs/2306.15518
Autor:
Vaghefi, Saeid Ashraf, Wang, Qian, Muccione, Veruska, Ni, Jingwei, Kraus, Mathias, Bingler, Julia, Schimanski, Tobias, Colesanti-Senni, Chiara, Webersinke, Nicolas, Huggel, Christrian, Leippold, Markus
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
Externí odkaz:
http://arxiv.org/abs/2304.05510
Autor:
Kraus, Mathias, Bingler, Julia Anna, Leippold, Markus, Schimanski, Tobias, Senni, Chiara Colesanti, Stammbach, Dominik, Vaghefi, Saeid Ashraf, Webersinke, Nicolas
Large language models (LLMs) have significantly transformed the landscape of artificial intelligence by demonstrating their ability in generating human-like text across diverse topics. However, despite their impressive capabilities, LLMs lack recent
Externí odkaz:
http://arxiv.org/abs/2304.00116