Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models

The relentless expansion of scientific literature presents significant challenges for navigation and knowledge discovery. Within Research Information Retrieval, established tasks such as text summarization and classification remain crucial for enabling researchers and practitioners to effectively navigate this vast landscape, so that efforts have increasingly been focused on developing advanced research information systems. These systems aim not only to provide standard keyword-based search functionalities but also to incorporate capabilities for automatic content categorization within knowledge-intensive organizations across academia and industry. This study systematically evaluates the performance of off-the-shelf Large Language Models (LLMs) in analyzing scientific texts according to a given classification scheme. We utilized the hierarchical ORKG taxonomy as a classification framework, employing the FORC dataset as ground truth. We investigated the effectiveness of advanced prompt engineering strategies, namely In-Context Learning (ICL) and Prompt Chaining, and experimentally explored the influence of the LLMs' temperature hyperparameter on classification accuracy. Our experiments demonstrate that Prompt Chaining yields superior classification accuracy compared to pure ICL, particularly when applied to the nested structure of the ORKG taxonomy. LLMs with prompt chaining outperform the state-of-the-art models for domain (1st level) prediction and show even better performance for subject (2nd level) prediction compared to the older BERT model. However, LLMs are not yet able to perform well in classifying the topic (3rd level) of research areas based on this specific hierarchical taxonomy, as they only reach about 50% accuracy even with prompt chaining.

Enhancing Research Information Systems with Identification of Domain Experts

Research organisations and their research outputs have been growing considerably in the past decades. This large body of knowledge attracts various stakeholders, e.g., for knowledge sharing, technology transfer, or potential collaborations. However, due to the large amount of complex knowledge created, traditional methods of manually curating catalogues are often out of time, imprecise, and cumbersome. Finding domain experts and knowledge within any larger organisation, scientific and also industrial, has thus become a serious challenge. Hence, exploring an institutions domain knowledge and finding its experts can only be solved by an automated solution. This work presents the scheme of an automated approach for identifying scholarly experts based on their publications and, prospectively, their teaching materials. Based on a search engine, this approach is currently being implemented for two universities, for which some examples are presented. The proposed system will be helpful for finding peer researchers as well as starting points for knowledge exploitation and technology transfer. As the system is designed in a scalable manner, it can easily include additional institutions and hence provide a broader coverage of research facilities in the future.