Get started
Author

Hinrich Schütze

Observed names: Hinrich Schuetze, Schütze, Hinrich
OpenAlex ID: A5122974599
Locate, steer, and improve: A practical survey of actionable mechanistic interpretability in large language models
2026 · Hengyuan Zhang, Zhihao Zhang, et al. · Computer Science Review · 32
High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
2026 · Liu, Yongkang, Li, Xing, et al. · arXiv (Cornell University) · 6
PDF
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
2026 · Wang, Zijing, Liu, Yongkang, et al. · arXiv (Cornell University) · 3
PDF
Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations
2026 · Yuxi Xia, Dennis Ulmer, et al. · 3
PDF
DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
2026 · Wang, Zijing, Wang, Mingyang, et al. · arXiv (Cornell University) · 2
PDF
Relational Linearity is a Predictor of Hallucinations
2026 · Yuetian Lu, Yihong Liu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2
PDF
Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence
2026 · Sebastian Gerstner, Hilal AlQuabeh, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2
PDF
Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models
2026 · Yang, Zhiqing, Liu, Yilun, et al. · arXiv (Cornell University) · 1
PDF
Left, Right, or Center? Evaluating LLM Framing in News Classification and Generation
2026 · Kennedy, Molly, Parker, Ali, et al. · arXiv (Cornell University) · 1
PDF
Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs
2026 · Jiaqiao Zhang, Zhoujun Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty
2026 · Kim, Hazel H., Binkowski, Jakub, et al. · arXiv (Cornell University)
PDF
Predicting Linear Relational Decodability Without the Relation
2026 · Rohweder, Jonas, Mülthaler, Adrian, et al. · arXiv (Cornell University)
PDF
Knowledge That Is Linear Before Fine-Tuning Generalizes After It
2026 · Mehri, Faridoun, Schütze, Hinrich · arXiv (Cornell University)
PDF
FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect
2026 · Kim, Hazel H., Bean, Andrew M., et al. · arXiv (Cornell University)
PDF
A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models
2026 · Qi, Jirui, Wang, Mingyang, et al. · arXiv (Cornell University)
PDF
Parsing Middle High German: exploring cross-lingual NLP for treebank construction in low-resource historical languages
2026 · Ercong Nie, Siyao Peng, et al. · Digital Scholarship in the Humanities
Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
2026 · Zhang, Shengqiang, Liao, Ruotong, et al. · arXiv (Cornell University)
PDF
ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation
2026 · Zhao, Raoyuan, Liu, Yihong, et al. · arXiv (Cornell University)
PDF
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
2026 · Liu, Yongkang, Wang, Zijing, et al. · arXiv (Cornell University)
PDF
The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing
2026 · Cao, Yuan, Wang, Mingyang, et al. · arXiv (Cornell University)
PDF
A Target-Centric Survey of Quantization-Aware Training
2026 · Jiamin Song, Mengjie Zhao, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 21
Citation count: 53
H-index: 3
I10-index: 1
Year
Topic
Type