Domain-Specific Question-Answering Systems: A Case Study of a Carbon Neutrality Knowledge Base

Lei Liu, Yongzhang Zhou (), Jianhua Ma, Yuqing Zhang and Luhao He ()
Additional contact information
Lei Liu: Center for Earth Environment & Resources, Sun Yat-sen University, Zhuhai 519000, China
Yongzhang Zhou: Center for Earth Environment & Resources, Sun Yat-sen University, Zhuhai 519000, China
Jianhua Ma: Center for Earth Environment & Resources, Sun Yat-sen University, Zhuhai 519000, China
Yuqing Zhang: Center for Earth Environment & Resources, Sun Yat-sen University, Zhuhai 519000, China
Luhao He: Center for Earth Environment & Resources, Sun Yat-sen University, Zhuhai 519000, China

Sustainability, 2025, vol. 17, issue 5, 1-23

Abstract: Carbon neutrality is a critical global objective in the fight against climate change. As relevant knowledge and technologies advance rapidly, there is an escalating demand for sophisticated intelligent services. While large language models (LLMs) have demonstrated considerable promise in knowledge processing and generation, their application within the domain of carbon neutrality remains in the early stages of exploration. This study develops a carbon neutrality knowledge base (CN Knowledge Base) using the ChatGLM3 model aimed at enhancing question-answering capabilities in areas such as carbon emission monitoring, policy interpretation, and technical optimization. By refining domain-specific corpora and integrating a Retrieval-Augmented Generation (RAG) mechanism, the model’s ability to generate accurate and relevant responses is improved. To evaluate the performance of the proposed system, a comprehensive quantitative comparison is conducted using established evaluation metrics, including BLEU (Bilingual Evaluation Understudy), BERT (Bidirectional Encoder Representations from Transformers), and METEOR (Metric for Evaluation of Translation with Explicit Ordering). The CN Knowledge Base is benchmarked against leading models such as GPT-4, Gemini, and Bing. The results demonstrate that the CN Knowledge Base outperforms other models in METEOR (0.2697) and is comparable to GPT-4o in both BLEU (0.8755) and BERT (0.8260) Scores (GPT-4o: BLEU: 0.8784, BERT: 0.8404). These findings underscore the knowledge base’s strong adaptability and its ability to generate high-quality, domain-specific content. The study suggests that specialized models can overcome the limitations of general-purpose LLMs, particularly in precise terminology and accurate application of domain knowledge. With continued development, such models could significantly enhance digital and intelligent solutions for carbon neutrality and related fields.

Keywords: domain-specific question answering; knowledge base construction; ChatGLM3; carbon neutrality; RAG (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/5/2192/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/5/2192/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:5:p:2192-:d:1604423

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().