Jiangfeng Liu

High-quality domain corpora constitute the cornerstone of computational humanities research. This study investigates the foundational methodologies and optimization strategies that leverage large language models (LLMs) in conjunction with prompt engineering to facilitate the construction and in-depth analysis of classical text corpora. The research systematically categorizes prevalent prompt frameworks and presents a comprehensive prompt optimization protocol, delineating common chain-of-thought enhancement approaches. It examines the application of prompt engineering-driven LLMs to address conventional natural language processing tasks for ancient texts. The study demonstrates the viability of prompt engineering methodologies based on large models for the intelligent processing and application of classical texts, offering relevant Artificial Intelligence (AI) digital humanities product exemplars as efficacious references for developing high-caliber corpora in the computational humanities domain. Future investigations should contemplate further exploration of AI technology’s potential in humanities scholarship, fostering interdisciplinary collaboration across humanities and social sciences disciplines, including history, literature, philosophy, computer science, and information science. Ongoing attention should be directed toward the technological impact on promoting and preserving exemplary traditional Chinese culture, ensuring judicious technological implementation alongside the safeguarding of traditional cultural knowledge and values.

Generative AI changes the paradigm of natural language processing research, sets off a new trend of research in computational humanities and computational social sciences, and provides unique perspectives on digital intelligence-enabled ancient book revitalization and intelligent applications. The article explores the role of multimodal large models in image processing and OCR of ancient books. We discuss and exemplify how to use Large Language Models for intelligent information processing of ancient texts and explore combining prompt engineering, retrieval augmented generation (RAG), supervised fine-tuning, LangChain, and other techniques to improve performance in ancient text mining and applications. This article also looks forward to the broad prospect of intelligent agent technology combined with the Large Language Model in the innovative application of ancient book revitalization. The research focuses on digitizing ancient books, intelligent processing of ancient texts, and intelligent application of ancient book revitalization. It demonstrates the feasibility, advancement, and creativity of the application of generative AI and its derivative technologies in the field of computational humanities, especially in the field of ancient book preservation, to provide intelligent solutions for the dissemination of traditional thought and culture, from the perspective of the whole process of the technology of digital humanities and computational humanities research. The article also gives examples of the intelligent application of AI in the restoration of ancient books and the annotation of ancient texts. Although Large Language Models demonstrate transformative potential in advancing the field of ancient text research toward intelligent analysis, there remain certain limitations. This article points out their shortcomings in areas such as knowledge completion for ancient texts, understanding emotions and cultural nuances, as well as ethical and accountability issues. It emphasizes the need for a more balanced perspective on the role that generative AI plays in the exploration and utilization of cultural heritage.

The rapid development of generative artificial intelligence has brought significant opportunities for the advancement of digital humanities research. Intelligent processing of ancient texts, as an essential part of digital humanities, is also undergoing a transformation in research methodologies in the wave of AIGC. The integration of generative pre-trained models with Chinese ancient texts, a vital carrier of Chinese culture, allows for deep mining of the content of these texts and provides services that make ancient texts more understandable and accessible to the general public. In this research, we propose a method that combines the most renowned Chinese anthology, the “Siku Quanshu,” with generative pre-trained models. We developed the SikuGPT model, a generative model for ancient text processing tasks, based on GPT-type language models by continued pretraining. This model was tested on two typical tasks of ancient text processing: translation between classical and modern Chinese, and classification of ancient texts. The findings reveal that our model achieves advantages in understanding and generating scenarios of ancient texts. The capability of SikuGPT in processing traditional Chinese texts helps to promote the organization of ancient information and knowledge services, and advances the international dissemination of traditional Chinese culture.

Purpose: The present study explores and investigates the efficiency of deep learning models in identifying discourse structure and functional features and explores the potential application of natural language processing (NLP) techniques in text mining, information measurement, and scientific communication.Method: The PLOS literature series has been utilized to obtain full-text data, and four deep learning models, including BERT, RoBERTa, SciBERT, and SsciBERT, have been employed for structure-function recognition.Result: The experimental findings reveal that the SciBERT model performs outstandingly, surpassing the other models, with an F1 score. Additionally, the performance of different paragraph structures has been analyzed, and it has been found that the model performs well in paragraphs such as method and result.Conclusion: The study's outcomes suggest that deep learning models can recognize the structure and functional elements at the discourse level, particularly for scientific literature, where the SciBERT model performs remarkably. Moreover, the NLP techniques have extensive prospects in various fields, including text mining, information measurement, and scientific communication. By automatically parsing and identifying structural and functional information in text, the efficiency of literature management and retrieval can be improved, thereby expediting scientific research progress. Therefore, deep learning and NLP technologies hold significant value in scientific research.