Preprints

• Shuzhou Yuan, William LaCroix, Hardik Ghoshal, Ercong Nie, Michael Färber. CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation. In arXiv 2025. [Paper]
• Shuzhou Yuan*, Ercong Nie*, Lukas Kouba, Ashish Yashwanth Kangen, Helmut Schmid, Hinrich Schütze, Michael Farber. LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification. In arXiv 2025. [Paper]
• Yongkang Liu, Xingle Xu, Ercong Nie, Zijing Wang, Shi Feng, Daling Wang, Qian Li, Hinrich Schütze. Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning. In arXiv 2025. [Paper]
• Shuzhou Yuan*, Ercong Nie*, Mario Tawfelis, Helmut Schmid, Hinrich Schütze, Michael Farber. Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models. In arXiv 2025. [Paper]
• Chunkit Chan, Yauwai Yim, Hongchuan Zeng, Zhiying Zou, Xinyuan Cheng, Zhifan Sun, Zheye Deng, Kawai Chung, Yuzhuo Ao, Yixiang Fan, Cheng Jiayang, Ercong Nie, Ginny Y Wong, Helmut Schmid, Hinrich Schütze, Simon See, Yangqiu Song. XToM: Exploring the Multilingual Theory of Mind for Large Language Models. In arXiv 2025. [Paper]
• Ercong Nie, Shuzhou Yuan, Bolei Ma, Helmut Schmid, Michael Färber, Frauke Kreuter, Hinrich Schütze. Decomposed prompting: Unveiling multilingual linguistic structure knowledge in english-centric large language models. In arXiv 2024. [Paper]

Datasets and Resources

• Jürg Fleischer, Lena Haden, Martin Klotz, Ercong Nie, Helmut Schmid, Gohar Schnelle, Lilian Slawski, and Lars Erik Zeige. Korpus Zur Erforschung Von Registerphänomenen Bei Martin Luther (regil). Zenodo 2025.

2025

• Ercong Nie, Helmut Schmid, Hinrich Schütze. Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models. In EMNLP 2025 Findings. [Paper]
• Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Felicia Körner, Ercong Nie, Barbara Plank, François Yvon, Hinrich Schütze. Tracing Multilingual Factual Knowledge Acquisition in Pretraining. In EMNLP 2025 Findings. [Paper]
• Ercong Nie*, Bo Shao*, Zifeng Ding, Mingyang Wang, Helmut Schmid, Hinrich Schütze. BMIKE-53: Investigating cross-lingual knowledge editing with in-context learning. In ACL 2025 (oral). [Paper], [Code]
• Linyang He, Ercong Nie, Helmut Schmid, Hinrich Schütze, Nima Mesgarani, Jonathan Brennan. Large Language Models as Neurolinguistic Subjects: Identifying Internal Representations for Form and Meaning. In ACL Findings 2025. [Paper]
• Mingyang Wang, Heike Adel, Lukas Lange, Yihong Liu, Ercong Nie, Jannik Strötgen, Hinrich Schütze. [Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models](https://aclanthology.org/2025.acl-long.253.pdf. In ACL 2025 [Paper]
• Linyang He*, Ercong Nie*, Sukru Samet Dindar, Arsalan Firoozi, Adrian Florea, Van Nguyen, Corentin Puffay, Riki Shimizu, Haotian Ye, Jonathan Brennan, Helmut Schmid, Hinrich Schütze, Nima Mesgarani. XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs. In ACL 2025 Workshop SIGTYP. [Paper]
• Lovisa Hagström, Ercong Nie, Ruben Halifa, Helmut Schmid, Richard Johansson, Alexander Junge. Language Model Re-rankers are Steered by Lexical Similarities. In ACL Workshop FEVER. [Paper]
• Shuzhou Yuan*, Ercong Nie*, Bolei Ma, Michael Färber. Why lift so heavy? slimming large language models by cutting off the layers. In IJCNN 2025. [Paper]

2024

• Shuzhou Yuan, Ercong Nie, Michael Färber, Helmut Schmid, Hinrich Schuetze. GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network. In ACL Findings 2024. [Paper], [Code]
• Huixin Chen, Jan Büssing, David Rügamer, Ercong Nie†. Team MGTD4ADL at SemEval-2024 Task 8: Leveraging (Sentence) Transformer Models with Contrastive Learning for Identifying Machine-Generated Text. In SemEval-2024@NAACL. [Paper]
• Linyang He, Peili Chen, Ercong Nie, Yuanning Li, Jonathan R. Brennan. Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models Using Minimal Pairs. In LREC-COLING 2024. [Paper]
• Yongkang Liu*, Ercong Nie*, Shi Feng, Zheng Hua, Zifeng Ding, Daling Wang, Yifei Zhang, Hinrich Schütze. A Unified Data Augmentation Framework for Low-Resource Multi-domain Dialogue Generation . In ECML-PKDD 2024. [Paper]
• Bolei Ma*, Ercong Nie*, Shuzhou Yuan, Helmut Schmid, Michael Färber, Frauke Kreuter, Hinrich Schuetze. ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks. In EACL 2024 (oral). [Paper], [Code]

2023

• Xiaoqian Li, Ercong Nie, Sheng Liang. From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL. In Instruction-2023@NeurIPS. [Paper]
• Ercong Nie, Helmut Schmid, Hinrich Schuetze. Unleashing the Multilingual Encoder Potential: Boosting Zero-Shot Performance via Probability Calibration. In EMNLP Findings 2023. [Paper], [Code]
• Zheyu Zhang*, Han Yang*, Bolei Ma*, David Rügamer, Ercong Nie†. Baby’s CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models. In CONLL-BabyLM 2023. [Paper]
• Xiaoqian Li, Ercong Nie, Sheng Liang. Crosslingual Retrieval Augmented In-context Learning for Bangla. In BLP-2023@EMNLP. [Paper]
• Ercong Nie, Helmut Schmid, Hinrich Schütze. Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach. In ALP-2023@RANLP. [Paper]
• Bolei Ma, Ercong Nie, Helmut Schmid, Hinrich Schuetze. Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding. In KONVENS 2023. [paper], [Code]
• Ercong Nie*, Sheng Liang*, Helmut Schmid, Hinrich Schütze. Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages. In ACL Findings 2023. [Paper], [Code]

2022

• Ingo Ziegler, Bolei Ma, Ercong Nie, Bernd Bischl, David Rügamer, Benjamin Schubert, Emilio Dorigatti. What cleaves? Is proteasomal cleavage prediction reaching a ceiling?. In LMRL-2022@NeurIPS. [Paper]
• Ercong Nie. Fine-Tuned Sentence Transformer Model for Question Answering Task. In StuTS 2022. [Paper]

(* denotes equal contribution, † denotes corresponding author.)