Keynote speakers

Yufang Hou

ITU Austria, Austria

Synthesizing Scientific Knowledge: From Biomedical Evidence to NLP Claims

Abstract

The exponential growth of scholarly literature poses a substantial challenge for researchers seeking to stay current with the latest findings and synthesize knowledge effectively. In this talk, I will first present our recent studies on supporting domain experts in synthesizing biomedical research findings, guided by established evidence synthesis principles for integrating and interpreting potentially biased and conflicting scientific evidence. Next, I will introduce our work on content meta-analysis in NLP literature, including building leaderboards and tracking the evolution of scientific claims over time. Finally, I will discuss open research challenges in modeling and reasoning over scientific knowledge encoded in scholarly documents.

Bio

Yufang Hou is a professor at IT:U – Interdisciplinary Transformation University Austria. At IT:U, she leads the NLP group with a strong focus on large language model (LLM) governance, computational argumentation, fact-checking, knowledge representation and reasoning, and human-centered NLP applications in science, health, and education. Yufang has served as an organizing committee member and senior program committee member for various NLP conferences, and has co-organized several workshops on topics such as argument mining, efficient NLP, and AI for Science.

Iryna Gurevych

Technical University of Darmstadt, Germany

Welcoming AI as a New Colleague: How Should We Evaluate AI for Science?

Abstract

AI is reshaping the work of researchers in real time. With the emergence of tools such as AI Scientist in 2024, a new era of AI-driven scientific discovery has begun. At the same time, high-profile venues are beginning to experiment with AI-assisted peer review. Yet the core question remains unresolved: How should we meaningfully evaluate AI for scientific work? In this talk, I will highlight challenges encountered in several projects focused on AI-assisted scientific communication and discuss how these challenges inform evaluation practices. I will examine methods for assessing AI-generated related-work sections and explore how automated reviewers can be evaluated with respect to research-design reasoning and novelty assessment. Together, these examples illustrate both the promise and the complexity of evaluating AI as it increasingly acts as a collaborator in scientific communication.

Bio

Iryna Gurevych is Professor of Ubiquitous Knowledge Processing in the Department of Computer Science at the Technical University of Darmstadt in Germany. She also is an adjunct professor at MBZUAI in Abu-Dhabi, UAE, and an affiliated professor at INSAIT in Sofia, Bulgaria. She is widely known for fundamental contributions to natural language processing (NLP) and machine learning. Professor Gurevych is a past president of the Association for Computational Linguistics (ACL), the leading professional society in NLP. Her many accolades include being a Fellow of the ACL, an ELLIS Fellow, and the recipient of an ERC Advanced Grant. Most recently, she has received the 2025 Milner award of the British Royal Society for her major contributions to NLP and artificial intelligence that combine deep understanding of human language and cognitive faculty with the latest paradigms in machine learning.