Welcome to the IT:U NLP Lab! Our overarching research goals are twofold: (a) to develop robust and trustworthy language processing techniques informed by linguistic principles for understanding and generating human language; and (b) to build human-centered NLP applications that advance education, social sciences, humanities, and scientific discovery. In pursuit of these research goals, our research agenda is center around the following topics:
Governance of Large Language Models (LLM): we will focus on evaluating and mitigating undesirable LLM behaviors, such as building LLM evaluation benchmarks and understanding the behaviors of LLMs with real-world knowledge conflicts.
Computational Argumentation and Fact-checking: we aim to combine argument mining and fact-checking technologies to combat real-world misinformation, such as detecting health and science misinformation.
NLP for Science: the goal is to develop reliable cross-document NLP techniques to support scientific research activities, including generating slides from scientific papers, building scientific leaderboards, generating citation text, synthesizing biomedical studies, and analyzing causal relations between scientific research concepts.
Knowledge and Reasoning: we aim to develop techniques that can effectively represent both explicit and implicit knowledge to perform complex reasoning tasks in situated contexts, such as designing a fallacious reasoning framework for misrepresented science and building an argumentation knowledge graph.
Recent News
04/2025: A warm welcome to Zhanting and Dmitry, who will be joining us as interns
03/2025: Minh and Debanjana have officially joined us at the IT:U-NLP Lab as our newest PhD students!
02/2025: Yufang gave an invited talk “Empowering Science with AI: Building NLP Models for Scientific Knowledge Synthesis and Fact-checking” at the Salzburg HCI Doctoral Consortium Week Winter 2024/2025 on Feb 25th.