default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDHinrich Schütze
Person information
- affiliation: Ludwig Maximilian University of Munich, Center for Information and Language Processing, Germany
- affiliation (former): University of Stuttgart, Institute for Natural Language Processing, Germany
- affiliation (former): Stanford University, CA, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
showing all ?? records
2020 – today
- 2026
[j39]Hengyuan Zhang, Zhihao Zhang, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Ercong Nie, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schütze, Xuanjing Huang, Qi Zhang, Ngai Wong:
Locate, steer, and improve: A practical survey of actionable mechanistic interpretability in large language models. Comput. Sci. Rev. 62: 101011 (2026)- [c333]Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt
, Nils Feldhus, Christin Seifert, Hinrich Schütze, Sebastian Möller, Vera Schmitt:
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation. ACL (1) 2026: 323-346 - [c332]Xiaowen Ma, Yunpu Ma, Chenyang Lin, Sikuan Yan, Jinhe Bi, Zixuan Cao, Yijun Tian, Volker Tresp, Hinrich Schütze:
Self-Evolving Multi-Agent Systems via Textual Backpropagation. ACL (Findings) 2026: 9918-9951 - [c331]Leonor Veloso, Hinrich Schütze:
GKnow: Measuring the Entanglement of Gender Bias and Factual Gender. ACL (1) 2026: 10240-10260 - [c330]Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schütze, Xuanjing Huang, Qi Zhang, Ngai Wong:
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models. ACL (Findings) 2026: 10317-10362 - [c329]Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Jinhe Bi, Kristian Kersting, Jeff Z. Pan, Hinrich Schütze, Volker Tresp, Yunpu Ma:
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning. ACL (1) 2026: 12805-12825 - [c328]Raoyuan Zhao, Yihong Liu, Lena Altinger, Hinrich Schütze, Michael A. Hedderich:
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors. ACL (1) 2026: 16059-16078 - [c327]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. ACL (1) 2026: 17681-17716 - [c326]Zijing Wang, Yongkang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schütze:
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs. ACL (Findings) 2026: 21019-21035 - [c325]Yihong Liu, Raoyuan Zhao, Hinrich Schütze, Michael A. Hedderich:
Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners. ACL (Findings) 2026: 22330-22358 - [c324]Yongkang Liu, Jiayang Yu, Mingyang Wang, Yiqun Zhang, Ercong Nie, Shi Feng, Daling Wang, Kaisong Song, Hinrich Schütze:
SAD: A Large-Scale Strategic Argumentative Dialogue Dataset. ACL (1) 2026: 36144-36164 - [c323]Zijing Wang, Xingle Xu, Yongkang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Daling Wang, Xiaocui Yang, Hinrich Schütze:
Why Do More Experts Fail? A Theoretical Analysis of Model Merging. ACL (1) 2026: 45460-45482 - [c322]Yongkang Liu, Xingle Xu, Ercong Nie, Zijing Wang, Shi Feng, Daling Wang, Qian Li, Hinrich Schütze:
Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning. ACL (1) 2026: 47800-47820 - [c321]Raoyuan Zhao, Yihong Liu, Hinrich Schütze, Michael A. Hedderich:
A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages. EACL (Findings) 2026: 5223-5247 - [c320]Pedro Henrique Luz de Araujo, Michael A. Hedderich, Ali Modarressi, Hinrich Schütze, Benjamin Roth:
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions. EACL (Volume 1: Long Papers) 2026: 5329-5359 - [c319]Marion Thaler, Abdullatif Köksal, Alina Leidinger, Anna Korhonen, Hinrich Schütze:
How Far Can Bias Go? Tracing Bias from Pre-Training Data to Alignment. LREC 2026: 3975-3995 - [c318]Abdullah Al Sefat, Amir Hossein Kargaran, François Yvon, Hinrich Schütze:
GlotWeb: Web Indexing for Minority Languages. WWW 2026: 8469-8472 - [i303]Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt, Nils Feldhus, Christin Seifert, Hinrich Schütze, Sebastian Möller, Vera Schmitt:
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation. CoRR abs/2601.00263 (2026) - [i302]Yihong Liu, Raoyuan Zhao, Hinrich Schütze, Michael A. Hedderich:
Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners. CoRR abs/2601.02996 (2026) - [i301]Molly Kennedy, Ali Parker, Yihong Liu, Hinrich Schütze:
Left, Right, or Center? Evaluating LLM Framing in News Classification and Generation. CoRR abs/2601.05835 (2026) - [i300]Yongkang Liu, Jiayang Yu, Mingyang Wang, Yiqun Zhang, Ercong Nie, Shi Feng, Daling Wang, Kaisong Song, Hinrich Schütze:
SAD: A Large-Scale Strategic Argumentative Dialogue Dataset. CoRR abs/2601.07423 (2026) - [i299]Yongkang Liu, Xing Li, Mengjie Zhao, Shanru Zhang, Zijing Wang, Qian Li, Shi Feng, Feiliang Ren, Daling Wang, Hinrich Schütze:
High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning. CoRR abs/2601.07507 (2026) - [i298]Zijing Wang, Yongkang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schütze:
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs. CoRR abs/2601.07645 (2026) - [i297]Yuxi Xia, Dennis Ulmer, Terra Blevins, Yihong Liu, Hinrich Schütze, Benjamin Roth:
Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations. CoRR abs/2601.08064 (2026) - [i296]Yuetian Lu, Yihong Liu, Hinrich Schütze:
Relational Linearity is a Predictor of Hallucinations. CoRR abs/2601.11429 (2026) - [i295]Yihong Liu, Bingyu Xiong, Hinrich Schütze:
Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models. CoRR abs/2601.12555 (2026) - [i294]Hengyuan Zhang, Zhihao Zhang, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Ercong Nie, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schütze, Xuanjing Huang, Qi Zhang, Ngai Wong:
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models. CoRR abs/2601.14004 (2026) - [i293]Zeinab Sadat Taghavi, Ali Modarressi, Hinrich Schütze, Andreas Marfurt:
With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots. CoRR abs/2602.09616 (2026) - [i292]Sebastian Gerstner, Hinrich Schütze:
GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models. CoRR abs/2602.23826 (2026) - [i291]Yana Veitsman, Yihong Liu, Hinrich Schütze:
Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders. CoRR abs/2603.18863 (2026) - [i290]Yuan Cao, Mingyang Wang, Hinrich Schütze:
The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing. CoRR abs/2603.20795 (2026) - [i289]Amir Hossein Kargaran, Nafiseh Nikeghbal, Jana Diesner, François Yvon, Hinrich Schütze:
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts. CoRR abs/2604.12978 (2026) - [i288]Ahmad Dawar Hakimi, Lea Hirlimann, Isabelle Augenstein, Hinrich Schütze:
Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection. CoRR abs/2604.13899 (2026) - [i287]Yihong Liu, Raoyuan Zhao, Michael A. Hedderich, Hinrich Schütze:
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning. CoRR abs/2605.09548 (2026) - [i286]Leonor Veloso, Hinrich Schütze:
GKnow: Measuring the Entanglement of Gender Bias and Factual Gender. CoRR abs/2605.12299 (2026) - [i285]Zijing Wang, Mingyang Wang, Ercong Nie, Yongkang Liu, Shi Feng, Mengjie Zhao, Daling Wang, Xiaocui Yang, Hinrich Schütze:
DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging. CoRR abs/2605.12960 (2026) - [i284]Yongkang Liu, Xing Li, Mengjie Zhao, Shanru Zhang, Zijing Wang, Qian Li, Shi Feng, Feiliang Ren, Daling Wang, Hinrich Schütze:
SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning. CoRR abs/2605.21147 (2026) - [i283]Yongkang Liu, Zijing Wang, Mengjie Zhao, Ercong Nie, Mingyang Wang, Qian Li, Feiliang Ren, Shi Feng, Daling Wang, Hinrich Schütze:
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning. CoRR abs/2605.21177 (2026) - [i282]Raoyuan Zhao, Yihong Liu, Yupei Du, Hinrich Schütze, Michael A. Hedderich:
ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation. CoRR abs/2605.27709 (2026) - [i281]Jiaqiao Zhang, Zhoujun Li, Raoyuan Zhao, Jian Lan, Thomas Seidl, Michael A. Hedderich, Hinrich Schütze, Yihong Liu:
Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs. CoRR abs/2605.27715 (2026) - [i280]Sangwon Ryu, Yihong Liu, Mingyang Wang, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee, Hinrich Schütze:
Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization. CoRR abs/2606.01252 (2026) - [i279]Yuetian Lu, Ali Modarressi, Yihong Liu, Hinrich Schütze:
Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models. CoRR abs/2606.03780 (2026) - [i278]Renhao Pei, Yihong Liu, Sampo Pyysalo, Hinrich Schütze, Shaoxiong Ji:
Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation? CoRR abs/2606.03782 (2026) - [i277]Shengqiang Zhang, Ruotong Liao, Volker Tresp, Barbara Plank, Hinrich Schütze:
Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models. CoRR abs/2606.13558 (2026) - [i276]Ahmad Dawar Hakimi, Kaiwei Lei, Isabelle Augenstein, Hinrich Schütze:
Output Vector Editing for Memorization Mitigation in Large Language Models. CoRR abs/2606.18767 (2026) - [i275]Zhiqing Yang, Yilun Liu, Yunpu Ma, Volker Tresp, Hinrich Schütze:
Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models. CoRR abs/2606.21645 (2026) - [i274]Fares Fourati, Hinrich Schütze, Eyke Hüllermeier, Iryna Gurevych:
The Boundaries of Automation: A Theory of Persistent Human Participation. CoRR abs/2607.21547 (2026) - 2025
- [j38]Abdullatif Köksal, Marion Thaler, Ayyoob Imani, Ahmet Üstün, Anna Korhonen, Hinrich Schütze:
MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions. Trans. Assoc. Comput. Linguistics 13: 1032-1055 (2025) - [j37]Ingo Ziegler, Abdullatif Köksal, Desmond Elliott, Hinrich Schütze:
CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation. Trans. Assoc. Comput. Linguistics 13: 1693-1721 (2025) - [j36]Ali Modarressi, Abdullatif Köksal, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze:
MemLLM: Finetuning LLMs to Use Explicit Read-Write Memory. Trans. Mach. Learn. Res. 2025 (2025) - [c317]Enes Özeren, Yihong Liu, Hinrich Schütze:
HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization. ACL (4) 2025: 79-96 - [c316]Qi Feng, Yihong Liu, Hinrich Schütze:
Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding. ACL (4) 2025: 222-239 - [c315]Yihong Liu, Haotian Ye, Chunlan Ma, Mingyang Wang, Hinrich Schütze:
LangSAMP: Language-Script Aware Multilingual Pretraining. ACL (1) 2025: 1743-1770 - [c314]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. ACL (1) 2025: 5075-5094 - [c313]Renhao Pei, Yihong Liu, Peiqin Lin, François Yvon, Hinrich Schütze:
Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu. ACL (1) 2025: 8767-8788 - [c312]Mohsen Fayyaz, Ali Modarressi, Hinrich Schütze, Nanyun Peng:
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence. ACL (1) 2025: 9136-9152 - [c311]Ahmad Dawar Hakimi, Ali Modarressi, Philipp Wicke, Hinrich Schütze:
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models. ACL (Findings) 2025: 12633-12653 - [c310]Ercong Nie, Bo Shao, Mingyang Wang, Zifeng Ding, Helmut Schmid, Hinrich Schütze:
BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning. ACL (1) 2025: 16357-16374 - [c309]Linyang He, Ercong Nie, Helmut Schmid, Hinrich Schütze, Nima Mesgarani, Jonathan Brennan:
Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence. ACL (Findings) 2025: 19284-19302 - [c308]Amir Hossein Kargaran, Yihong Liu, François Yvon, Hinrich Schütze:
How Programming Concepts and Neurons Are Shared in Code Language Models. ACL (Findings) 2025: 26905-26917 - [c307]Amir Hossein Kargaran, Ali Modarressi, Nafiseh Nikeghbal, Jana Diesner, François Yvon, Hinrich Schütze:
MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment. ACL (Findings) 2025: 27001-27023 - [c306]Yihong Liu, Chunlan Ma, Haotian Ye, Hinrich Schütze:
TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data. COLING 2025: 469-495 - [c305]Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Ayyoob Imani, Orgest Xhelili, Haotian Ye, Chunlan Ma, François Yvon, Hinrich Schütze:
How Transliterations Improve Crosslingual Alignment. COLING 2025: 2417-2433 - [c304]Ercong Nie, Helmut Schmid, Hinrich Schütze:
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models. EMNLP (Findings) 2025: 690-706 - [c303]Yihong Liu, Runsheng Chen, Lea Hirlimann, Ahmad Dawar Hakimi, Mingyang Wang, Amir Hossein Kargaran, Sascha Rothe, François Yvon, Hinrich Schütze:
On Relation-Specific Neurons in Large Language Models. EMNLP 2025: 992-1022 - [c302]Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Felicia Körner, Ercong Nie, Barbara Plank, François Yvon, Hinrich Schütze:
Tracing Multilingual Factual Knowledge Acquisition in Pretraining. EMNLP (Findings) 2025: 2121-2146 - [c301]Mingyang Wang, Lukas Lange, Heike Adel, Yunpu Ma, Jannik Strötgen, Hinrich Schütze:
Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes. EMNLP 2025: 2637-2665 - [c300]Raoyuan Zhao, Abdullatif Köksal, Ali Modarressi, Michael A. Hedderich, Hinrich Schütze:
Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing. EMNLP (Findings) 2025: 23254-23280 - [c299]Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma, Hinrich Schütze:
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge. EMNLP 2025: 33168-33190 - [c298]Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Trung Bui, Ryan A. Rossi, Seunghyun Yoon, Hinrich Schütze:
NoLiMa: Long-Context Evaluation Beyond Literal Matching. ICML 2025 - [c297]Ercong Nie, Shuzhou Yuan, Bolei Ma, Helmut Schmid, Michael Färber, Frauke Kreuter, Hinrich Schütze:
Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models. IJCNLP-AACL (Findings) 2025: 646-659 - [c296]Shuzhou Yuan, Ercong Nie, Lukas Kouba, Helmut Schmid, Hinrich Schütze, Michael Färber:
LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification. IJCNLP-AACL (Findings) 2025: 1014-1027 - [c295]Ivo De Souza Bueno Júnior, Haotian Ye, Axel Wisiorek, Hinrich Schütze:
Privacy-Preserving Federated Learning for Hate Speech Detection. NAACL (Student Research Workshop) 2025: 129-141 - [c294]Chunlan Ma, Ayyoob Imani, Haotian Ye, Renhao Pei, Ehsaneddin Asgari, Hinrich Schütze:
Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages. NAACL (Short Papers) 2025: 414-439 - [c293]Peiqin Lin, André F. T. Martins, Hinrich Schütze:
XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples. NAACL (Findings) 2025: 3968-3977 - [c292]Peiqin Lin, André F. T. Martins, Hinrich Schütze:
A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models. NAACL (Findings) 2025: 4038-4050 - [c291]Xinpeng Wang, Mingyang Wang, Yihong Liu, Hinrich Schütze, Barbara Plank:
Refusal Direction is Universal Across Safety-Aligned Languages. NeurIPS 2025 - [i273]Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Trung Bui, Ryan A. Rossi, Seunghyun Yoon, Hinrich Schütze:
NoLiMa: Long-Context Evaluation Beyond Literal Matching. CoRR abs/2502.05167 (2025) - [i272]Renhao Pei, Yihong Liu, Peiqin Lin, François Yvon, Hinrich Schütze:
Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu. CoRR abs/2502.11862 (2025) - [i271]Mingyang Wang, Alisa Stoll, Lukas Lange, Heike Adel, Hinrich Schütze, Jannik Strötgen:
Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion. CoRR abs/2502.12598 (2025) - [i270]Yihong Liu, Runsheng Chen, Lea Hirlimann, Ahmad Dawar Hakimi, Mingyang Wang, Amir Hossein Kargaran, Sascha Rothe, François Yvon, Hinrich Schütze:
On Relation-Specific Neurons in Large Language Models. CoRR abs/2502.17355 (2025) - [i269]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. CoRR abs/2502.19737 (2025) - [i268]Mohsen Fayyaz, Ali Modarressi, Hinrich Schütze, Nanyun Peng:
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence. CoRR abs/2503.05037 (2025) - [i267]Molly Kennedy, Ayyoob Imani, Timo Spinde, Hinrich Schütze:
Through the LLM Looking Glass: A Socratic Self-Assessment of Donkeys, Elephants, and Markets. CoRR abs/2503.16674 (2025) - [i266]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. CoRR abs/2504.04264 (2025) - [i265]Enes Özeren, Yihong Liu, Hinrich Schütze:
HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization. CoRR abs/2504.21018 (2025) - [i264]Jinhe Bi, Danqi Yan, Yifan Wang, Wenke Huang, Haokun Chen, Guancheng Wan, Mang Ye, Xun Xiao, Hinrich Schütze, Volker Tresp, Yunpu Ma:
CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process. CoRR abs/2505.13408 (2025) - [i263]Qianli Wang, Mingyang Wang, Nils Feldhus, Simon Ostermann, Yuan Cao, Hinrich Schütze, Sebastian Möller, Vera Schmitt:
Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability. CoRR abs/2505.13963 (2025) - [i262]Mingyang Wang, Lukas Lange, Heike Adel, Yunpu Ma, Jannik Strötgen, Hinrich Schütze:
Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes. CoRR abs/2505.14815 (2025) - [i261]Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Felicia Körner, Ercong Nie, Barbara Plank, François Yvon, Hinrich Schütze:
Tracing Multilingual Factual Knowledge Acquisition in Pretraining. CoRR abs/2505.14824 (2025) - [i260]Ercong Nie, Helmut Schmid, Hinrich Schütze:
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models. CoRR abs/2505.16538 (2025) - [i259]Xinpeng Wang, Mingyang Wang, Yihong Liu, Hinrich Schütze, Barbara Plank:
Refusal Direction is Universal Across Safety-Aligned Languages. CoRR abs/2505.17306 (2025) - [i258]Sebastian Gerstner, Hinrich Schütze:
Understanding Gated Neurons in Transformers from Their Input-Output Functionality. CoRR abs/2505.17936 (2025) - [i257]Zijing Wang, Xingle Xu, Yongkang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Xiaocui Yang, Daling Wang, Hinrich Schütze:
Why Do More Experts Fail? A Theoretical Analysis of Model Merging. CoRR abs/2505.21226 (2025) - [i256]Raoyuan Zhao, Abdullatif Köksal, Ali Modarressi, Michael A. Hedderich, Hinrich Schütze:
Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing. CoRR abs/2505.21701 (2025) - [i255]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. CoRR abs/2505.22355 (2025) - [i254]Tobias Lindenbauer, Georg Groh, Hinrich Schütze:
From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents. CoRR abs/2505.23422 (2025) - [i253]Amir Hossein Kargaran, Yihong Liu, François Yvon, Hinrich Schütze:
How Programming Concepts and Neurons Are Shared in Code Language Models. CoRR abs/2506.01074 (2025) - [i252]Shuzhou Yuan, Ercong Nie, Lukas Kouba, Ashish Yashwanth Kangen, Helmut Schmid, Hinrich Schütze, Michael Färber:
LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification. CoRR abs/2506.01484 (2025) - [i251]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. CoRR abs/2506.02461 (2025) - [i250]Ahmad Dawar Hakimi, Ali Modarressi, Philipp Wicke, Hinrich Schütze:
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models. CoRR abs/2506.03434 (2025) - [i249]Shuzhou Yuan, Ercong Nie, Mario Tawfelis, Helmut Schmid, Hinrich Schütze, Michael Färber:
Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models. CoRR abs/2506.08593 (2025) - [i248]Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma, Hinrich Schütze:
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge. CoRR abs/2506.14407 (2025) - [i247]Qi Feng, Yihong Liu, Hinrich Schütze:
Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding. CoRR abs/2507.09758 (2025) - [i246]Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Hinrich Schütze, Volker Tresp, Yunpu Ma:
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning. CoRR abs/2508.19828 (2025) - [i245]Han Yang, Jian Lan, Yihong Liu, Hinrich Schütze, Thomas Seidl:
Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach. CoRR abs/2508.21206 (2025) - [i244]Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Ryan A. Rossi, Trung Bui, Hinrich Schütze, Nanyun Peng:
Steering MoE LLMs via Expert (De)Activation. CoRR abs/2509.09660 (2025) - [i243]Leonor Veloso, Lea Hirlimann, Philipp Wicke, Hinrich Schütze:
SLAyiNG: Towards Queer Language Processing. CoRR abs/2509.17449 (2025) - [i242]Liang Chen, Xueting Han, Qizhou Wang, Bo Han, Jing Bai, Hinrich Schütze, Kam-Fai Wong:
EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget. CoRR abs/2510.05837 (2025) - [i241]Philipp Mondorf, Mingyang Wang, Sebastian Gerstner, Ahmad Dawar Hakimi, Yihong Liu, Leonor Veloso, Shijia Zhou, Hinrich Schütze, Barbara Plank:
BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods. CoRR abs/2510.06811 (2025) - [i240]Yihong Liu, Raoyuan Zhao, Lena Altinger, Hinrich Schütze, Michael A. Hedderich:
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors. CoRR abs/2510.09536 (2025) - [i239]Raoyuan Zhao, Yihong Liu, Hinrich Schütze, Michael A. Hedderich:
A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages. CoRR abs/2510.09555 (2025) - [i238]Yihong Liu, Mingyang Wang, François Yvon, Hinrich Schütze:
On the Entity-Level Alignment in Crosslingual Consistency. CoRR abs/2510.10280 (2025) - [i237]Jian Lan, Zhicheng Liu, Udo Schlegel, Raoyuan Zhao, Yihong Liu, Hinrich Schütze, Michael A. Hedderich, Thomas Seidl:
Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering. CoRR abs/2510.11295 (2025) - [i236]Pedro Henrique Luz de Araujo, Michael A. Hedderich, Ali Modarressi, Hinrich Schütze, Benjamin Roth:
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions. CoRR abs/2512.12775 (2025) - 2024
- [j35]Valentin Hofmann, Goran Glavas, Nikola Ljubesic, Janet B. Pierrehumbert, Hinrich Schütze:
Geographic Adaptation of Pretrained Language Models. Trans. Assoc. Comput. Linguistics 12: 411-431 (2024) - [c290]Amir Hossein Kargaran, François Yvon, Hinrich Schütze:
MaskLID: Code-Switching Language Identification through Iterative Masking. ACL (Short Papers) 2024: 459-469 - [c289]Yihong Liu, Chunlan Ma, Haotian Ye, Hinrich Schütze:
TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models. ACL (1) 2024: 2476-2499 - [c288]Shuzhou Yuan, Ercong Nie, Michael Färber, Helmut Schmid, Hinrich Schütze:
GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network. ACL (Findings) 2024: 3987-4001 - [c287]Paul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck, Hannah Kirk, Hinrich Schütze, Dirk Hovy:
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models. ACL (1) 2024: 15295-15311 - [c286]Shijia Zhou, Leonie Weissweiler, Taiqi He, Hinrich Schütze, David R. Mortensen, Lori S. Levin:
Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons. LREC/COLING 2024: 3804-3811 - [c285]Amir Hossein Kargaran, François Yvon, Hinrich Schütze:
GlotScript: A Resource and Tool for Low Resource Writing System Identification. LREC/COLING 2024: 7774-7784 - [c284]Verena Blaschke, Barbara Kovacic, Siyao Peng, Hinrich Schütze, Barbara Plank:
MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank. LREC/COLING 2024: 10921-10938 - [c283]Abdullatif Köksal, Silvia Severini, Hinrich Schütze:
SilverAlign: MT-Based Silver Data Algorithm for Evaluating Word Alignment. LREC/COLING 2024: 14812-14825 - [c282]Leonie Weissweiler, Nina Böbel, Kirian Guiller, Santiago Herrera, Wesley Samuel Scivetti, Arthur Lorenzi Almeida, Nurit Melnik, Archna Bhatia, Hinrich Schütze, Lori S. Levin, Amir Zeldes, Joakim Nivre, William Croft, Nathan Schneider:
UCxn: Typologically-Informed Annotation of Constructions Atop Universal Dependencies. LREC/COLING 2024: 16919-16932 - [c281]David R. Mortensen, Valentina Izrailevitch, Yunze Xiao, Hinrich Schütze, Leonie Weissweiler:
Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs. LREC/COLING 2024: 17359-17364 - [c280]Peiqin Lin, Chengzhi Hu, Zheyu Zhang, André F. T. Martins, Hinrich Schütze:
mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models. EACL (Findings) 2024: 276-310 - [c279]Lütfi Kerem Senel, Benedikt Ebing, Konul Baghirova, Hinrich Schütze, Goran Glavas:
Kardeş-NLU: Transfer to Low-Resource Languages with Big Brother's Help - A Benchmark and Evaluation for Turkic Languages. EACL (1) 2024: 1672-1688 - [c278]Bolei Ma, Ercong Nie, Shuzhou Yuan, Helmut Schmid, Michael Färber, Frauke Kreuter, Hinrich Schütze:
ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks. EACL (1) 2024: 2685-2702 - [c277]Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schütze:
ChatZero: Zero-Shot Cross-Lingual Dialogue Generation via Pseudo-Target Language. ECAI 2024: 3867-3874 - [c276]Raoyuan Zhao, Abdullatif Köksal, Yihong Liu, Leonie Weissweiler, Anna Korhonen, Hinrich Schütze:
SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic Evaluation. EMNLP (Findings) 2024: 7017-7034 - [c275]Arda Yüksel, Abdullatif Köksal, Lütfi Kerem Senel, Anna Korhonen, Hinrich Schütze:
TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish. EMNLP (Findings) 2024: 7035-7055 - [c274]Abdullatif Köksal, Timo Schick, Anna Korhonen, Hinrich Schütze:
LongForm: Effective Instruction Tuning with Reverse Instructions. EMNLP (Findings) 2024: 7056-7078 - [c273]Mingyang Wang, Lukas Lange, Heike Adel, Jannik Strötgen, Hinrich Schütze:
Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization. EMNLP (Findings) 2024: 7990-8000 - [c272]Orgest Xhelili, Yihong Liu, Hinrich Schütze:
Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment. EMNLP (Findings) 2024: 11283-11296 - [c271]Ali Modarressi, Abdullatif Köksal, Hinrich Schütze:
Consistent Document-level Relation Extraction via Counterfactuals. EMNLP (Findings) 2024: 11501-11507 - [c270]Yongkang Liu, Yiqun Zhang, Qian Li, Tong Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schütze:
HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy. EMNLP 2024: 18266-18287 - [c269]Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schütze:
Rehearsal-Free Modular and Compositional Continual Learning for Language Models. NAACL (Short Papers) 2024: 469-480 - [c268]Yihong Liu, Peiqin Lin, Mingyang Wang, Hinrich Schütze:
OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining. NAACL-HLT (Findings) 2024: 1067-1097 - [c267]Amir Hossein Kargaran, François Yvon, Hinrich Schütze:
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages. NeurIPS 2024 - [c266]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. ECML/PKDD (2) 2024: 162-177 - [e3]Cristina Piazza, Patricia Capsi-Morales, Luis Figuer