Welcome!

I am leading the WeNLP4Science Research Group at the University of Aberdeen, and an Invited Lecturer in Computational Linguistics at Heidelberg University. Our research group has broad interests in NLP/LLMs and Machine Learning (e.g., evaluation, cross-temporal NLP and geometric ML), and we recently blend our expertise into LLMs for Science, with a focus on post-training, evaluation and applications of LLMs in scientific and industrial domains.

Previously, I was an Invited Postdoc at Heidelberg Institute for Theoretical Studies (HITS) and Heidelberg University, working on the Geometry and Representation Learning. In December 2022, I earned my Ph.D. in NLP from the AIPHES Training Group at TU Darmstadt, Germany.

Recent News

08/2025: Two papers about tokenization for temporal reasoning and evaluation of LLMs accepted at EMNLP

05/2025: Our workshop on Towards Human-LLM Collaboration for Ethical and Responsible Science Production will be held at IJCNLP-AACL

05/2025: Our workshop on LLMs for Cross-Temporal Research will be held at COLM

04/2025: Recipient of Outstanding Paper Award at NAACL

04/2025: Recipient of Computing Grant from Google

03/2025: Recipient of Sponsorship Funding from Artificial Intelligence Journal

02/2025: Recipient of Research Catalyst Funding from the University of Aberdeen

01/2025: A paper about evaluation of LLMs accepted at NAACL

01/2025: Recipient of Computing Credits from OpenAI

12/2024: A paper nominated by ARR Area Chair for Best Paper Award

12/2024: Two papers about LLMs for human annotation accepted at the CoMeDi Workshop, co-located with COLING

08/2024: Recipient of Research Collaboration Grant from the Royal Society of Edinburgh

07/2024: A paper about LLMs for lexicography accepted at the LLM-LEX Workshop, co-located with EURALEX

07/2024: Recipient of Computing Credits from Google

06/2024: Three papers about cross-temporal research accepted at the LChange Workshop, co-located with ACL

04/2024: A paper about graph embedding accepted at TMLR

02/2024: A paper about evaluation of LLMs accepted at JMLR

01/2024: A paper about cross-temporal research accepted at EACL

01/2024: Joined the University of Aberdeen

Selected Publications

How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs - Ran Zhang, Wei Zhao, Steffen Eger, NAACL 2025, Outstanding Paper Award

Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation - Steffen Eger, Yong Cao, Jennifer D'Souza, Andreas Geiger, Christian Greisinger, Stephanie Gross, Yufang Hou, Brigitte Krenn, Anne Lauscher, Yizhi Li, Chenghua Lin, Nafise Sadat Moosavi, Wei Zhao, Tristan Miller, preprint, 02/2025

WeNLP4Science Research Group

PhD Researchers

Yujun Wang
University of Aberdeen

Owusu-Banahene Osei
University of Aberdeen

Ran Zhang (Partially Co-supervised)
University of Mannheim

MSC/BSC Thesis Students

Melis Çelikkol (MSC)
Heidelberg University

Lydia Körber (MSC)
Heidelberg University

Nathan Begley (BSC)
University of Aberdeen

Nusrath Jinnath (BSC)
University of Aberdeen

Carlos Gomez Aryoshi (BSC)
University of Aberdeen

Ishaq Ali (BSC)
University of Aberdeen

Teaching

CS4051: Natural Language Processing (2024-2025) at Aberdeen

CS5063: Evaluation of AI Systems (2024-2026) at Aberdeen

CS551N: Introduction to Programming (2024-2026) at Aberdeen

CS551P: Advanced Programming (2024-2025) at Aberdeen

PS/HS: Diachronic Language Models (2023-2025) at Heidelberg

PS/HS: Cross-Temporal NLP (2025-2026) at Heidelberg

Open Positions

Media

10/2024: Large Language Models No Match for Humans in Literary Translation, Slator

05/2025: QA-Based Evaluation Takes on Literary AI Translation, Slator

Acknowledgements