On October 30, the third SCOR online seminar took place, featuring a presentation by Dr. Tarcisio Mendes de Farias from the Swiss Institute of Bioinformatics (SIB). His talk examined the interplay between ontologies, knowledge representation, and Large Language Models (LLMs), shedding light on current challenges and opportunities in this rapidly evolving research domain. The seminar attracted approximately 60 participants, reflecting the growing academic interest in integrating ontologies and artificial intelligence.
The abstract and recording of his talk are available below. If you’d like to stay updated about upcoming SCOR online seminars and other SCOR-related events, you can subscribe to our newsletter (at the bottom of the homepage) and/or follow us on LinkedIn: https://www.linkedin.com/company/swissonto/.
Tarcisio Mendes de Farias (SIB Swiss Institute of Bioinformatics)
“Knowledge Representation and Ontologies in the Era of Large Language Models”
Abstract
With the advent of large language models (LLMs), we are currently able to build applications with a relatively good accuracy that can process and generate “human”-like text, engage in natural language conversations, and perform several types of tasks based on users’ prompts. Nevertheless, it is well known that LLMs and their applications can have several limitations among them: hallucinations, indecisiveness, a “black-box” approach and lacking domain-specific knowledge. To address these limitations and more, the knowledge representation with ontologies can play a key role by making it possible to use and enhance LLMs for challenging applications that demand a high accuracy and verifiable outcomes. One of these applications is scientific question answering. In this talk, I will present different strategies to address the LLM limitations such as fine- and prompt-tuning, discuss effective relations between ontologies and LLMs, and our latest work on building a question answering system over scientific data in the form of knowledge graphs. In this recent work, we also seek to leverage the ontologies used to build these knowledge graphs.
Short bio
Dr. Tarcisio Mendes de Farias is a team leader and a computer scientist by training at the SIB Swiss Institute of Bioinformatics. He co-leads the Knowledge Representation Unit (https://www.sib.swiss/community/our-groups/vital-it/knowledge-representation-unit) at SIB. Currently, he is a PI in several national and international research and infrastructure projects involving the R&D of advanced methodologies for ontology engineering, data management, semantic data interoperability and integration, and question answering systems based on large language models.