Katharina von der Wense

60 papers A* 10B 4Journal 31Unranked 15
YearRankTypeTitle / Venue / Authors
2026 J jnl
Greater accessibility can amplify discrimination in generative AI.
CoRR
Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou, Valentin Hofmann, Katharina von der Wense, Anne Lauscher
2026 J jnl
Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect.
CoRR
Minh Duc Bui, Manuel Mager, Peter Herbert Kann, Katharina von der Wense
2025 — conf
CLIX: Cross-Lingual Explanations of Idiomatic Expressions.
ACL (Findings)
Aaron Gluck, Katharina von der Wense, Maria Leonor Pacheco
2025 J jnl
CLIX: Cross-Lingual Explanations of Idiomatic Expressions.
CoRR
Aaron Gluck, Katharina von der Wense, Maria Leonor Pacheco
2025 J jnl
Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models.
CoRR
Mario Sanz-Guerrero, Katharina von der Wense
2025 B conf
From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation.
COLING
Ali Marashian, Enora Rice, Luke Gessler, Alexis Palmer, Katharina von der Wense
2025 A* conf
Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions.
IJCAI
Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette, Katharina von der Wense, Alessandro Roncone
2025 J jnl
Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions.
CoRR
Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette, Katharina von der Wense, Alessandro Roncone
2025 — conf
Improving Low-Resource Morphological Inflection via Self-Supervised Objectives.
ACL (1)
Adam Wiemerslage, Katharina von der Wense
2025 J jnl
Improving Low-Resource Morphological Inflection via Self-Supervised Objectives.
CoRR
Adam Wiemerslage, Katharina von der Wense
2025 A* conf
Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation.
EMNLP
Enora Rice, Katharina von der Wense, Alexis Palmer
2025 J jnl
Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation.
CoRR
Enora Rice, Katharina von der Wense, Alexis Palmer
2025 J jnl
JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA.
CoRR
Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, Katharina von der Wense
2025 A* conf
Large Language Models Discriminate Against Speakers of German Dialects.
EMNLP
Minh Duc Bui, Carolin Holtermann, Valentin Hofmann, Anne Lauscher, Katharina von der Wense
2025 J jnl
Large Language Models Discriminate Against Speakers of German Dialects.
CoRR
Minh Duc Bui, Carolin Holtermann, Valentin Hofmann, Anne Lauscher, Katharina von der Wense
2025 — conf
Linguistic Alignment Predicts Learning in Small Group Tutoring Sessions.
EMNLP (Findings)
Dorothea French, Robert G. Moulder, Kelechi Ezema, Katharina von der Wense, Sidney K. D'Mello
2025 — conf
MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset.
ACL (Findings)
Sagi Shaier, George Arthur Baker, Chiranthan Sridhar, Lawrence Hunter, Katharina von der Wense
2025 B conf
Measuring Contextual Informativeness in Child-Directed Text.
COLING
Maria R. Valentini, Téa Y. Wright, Ali Marashian, Jennifer Weber, Eliana Colunga, Katharina von der Wense
2025 A* conf
Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs.
EMNLP
Mario Sanz-Guerrero, Minh Duc Bui, Katharina von der Wense
2025 J jnl
Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs.
CoRR
Mario Sanz-Guerrero, Minh Duc Bui, Katharina von der Wense
2025 — conf
Mitigating Label Length Bias in Large Language Models.
IJCNLP-AACL (long papers)
Mario Sanz-Guerrero, Katharina von der Wense
2025 J jnl
Mitigating Label Length Bias in Large Language Models.
CoRR
Mario Sanz-Guerrero, Katharina von der Wense
2025 A* conf
Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer.
EMNLP
Abteen Ebrahimi, Adam Wiemerslage, Katharina von der Wense
2025 J jnl
Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer.
CoRR
Abteen Ebrahimi, Adam Wiemerslage, Katharina von der Wense
2025 A* conf
Molecular String Representation Preferences in Pretrained LLMs: A Comparative Study in Zero- & Few-Shot Molecular Property Prediction.
EMNLP
George Arthur Baker, Mario Sanz-Guerrero, Katharina von der Wense
2025 A* conf
More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed Routing.
ICLR
Sagi Shaier, Francisco Pereira, Katharina von der Wense, Lawrence Hunter, Matt Jones
2025 — conf
Multi³Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models.
NAACL (Long Papers)
Minh Duc Bui, Katharina von der Wense, Anne Lauscher
2025 J jnl
NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation.
CoRR
Hossain Shaikh Saadi, Faria Alam, Mario Sanz-Guerrero, Minh Duc Bui, Manuel Mager, Katharina von der Wense
2025 — conf
On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures.
ACL (1)
Minh Duc Bui, Kyung Eun Park, Goran Glavas, Fabian David Schmidt, Katharina von der Wense
2025 J jnl
On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures.
CoRR
Minh Duc Bui, Kyung Eun Park, Goran Glavas, Fabian David Schmidt, Katharina von der Wense
2025 A* conf
ReSeeding Latent States for Sequential Language Understanding.
EMNLP
Stéphane Aroca-Ouellette, Katharina von der Wense, Alessandro Roncone
2025 — conf
The Effectiveness of Uncased Tokeniziaion for Clinical Notes.
ACL (Findings)
Cory Paik, Katharina von der Wense
2025 — conf
Understanding the Gap: an Analysis of Research Collaborations in NLP and Language Documentation.
ACL (Findings)
Luke Gessler, Alexis Palmer, Katharina von der Wense
2025 J jnl
Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging.
CoRR
Enora Rice, Ali Marashian, Hannah J. Haynie, Katharina von der Wense, Alexis Palmer
2024 — conf
Comparing Template-based and Template-free Language Model Probing.
EACL (1)
Sagi Shaier, Kevin Bennett, Lawrence Hunter, Katharina von der Wense
2024 J jnl
Comparing Template-based and Template-free Language Model Probing.
CoRR
Sagi Shaier, Kevin Bennett, Lawrence E. Hunter, Katharina von der Wense
2024 — conf
Desiderata For The Context Use Of Question Answering Systems.
EACL (1)
Sagi Shaier, Lawrence Hunter, Katharina von der Wense
2024 J jnl
Desiderata for the Context Use of Question Answering Systems.
CoRR
Sagi Shaier, Lawrence E. Hunter, Katharina von der Wense
2024 B conf
Evaluating LLMs as Tools to Support Early Vocabulary Learning.
CogSci
Jennifer Weber, Maria R. Valentini, Téa Wright, Katharina von der Wense, Eliana Colunga
2024 B conf
Eyes on the Game: Deciphering Implicit Human Signals to Infer Human Proficiency, Trust, and Intent.
RO-MAN
Nikhil Hulle, Stéphane Aroca-Ouellette, Anthony J. Ries, Jake Brawer, Katharina von der Wense, Alessandro Roncone
2024 J jnl
Eyes on the Game: Deciphering Implicit Human Signals to Infer Human Proficiency, Trust, and Intent.
CoRR
Nikhil Hulle, Stéphane Aroca-Ouellette, Anthony J. Ries, Jake Brawer, Katharina von der Wense, Alessandro Roncone
2024 J jnl
From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation.
CoRR
Ali Marashian, Enora Rice, Luke Gessler, Alexis Palmer, Katharina von der Wense
2024 A* conf
Getting The Most Out of Your Training Data: Exploring Unsupervised Tasks for Morphological Inflection.
EMNLP
Abhishek Purushothama, Adam Wiemerslage, Katharina von der Wense
2024 J jnl
Identifying Telescope Usage in Astrophysics Publications: A Machine Learning Framework for Institutional Research Management at Observatories.
CoRR
Vicente Amado Olivo, Wolfgang E. Kerzendorf, Brian A. Cherinka, Joshua Shields, Annie Didier, Katharina von der Wense
2024 — conf
It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension.
ACL (Findings)
Sagi Shaier, Lawrence Hunter, Katharina von der Wense
2024 J jnl
It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension.
CoRR
Sagi Shaier, Lawrence E. Hunter, Katharina von der Wense
2024 J jnl
Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget.
CoRR
Minh Duc Bui, Fabian David Schmidt, Goran Glavas, Katharina von der Wense
2024 J jnl
Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA.
CoRR
George Arthur Baker, Ankush Raut, Sagi Shaier, Lawrence E. Hunter, Katharina von der Wense
2024 J jnl
MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset.
CoRR
Sagi Shaier, George Arthur Baker, Chiranthan Sridhar, Lawrence E. Hunter, Katharina von der Wense
2024 J jnl
Measuring Contextual Informativeness in Child-Directed Text.
CoRR
Maria R. Valentini, Téa Wright, Ali Marashian, Jennifer Weber, Eliana Colunga, Katharina von der Wense
2024 J jnl
More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing.
CoRR
Sagi Shaier, Francisco Pereira, Katharina von der Wense, Lawrence E. Hunter, Matt Jones
2024 J jnl
Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models.
CoRR
Minh Duc Bui, Katharina von der Wense, Anne Lauscher
2024 — conf
Quantifying the Hyperparameter Sensitivity of Neural Networks for Character-level Sequence-to-Sequence Tasks.
EACL (1)
Adam Wiemerslage, Kyle Gorman, Katharina von der Wense
2024 — conf
TAMS: Translation-Assisted Morphological Segmentation.
ACL (1)
Enora Rice, Ali Marashian, Luke Gessler, Alexis Palmer, Katharina von der Wense
2024 J jnl
TAMS: Translation-Assisted Morphological Segmentation.
CoRR
Enora Rice, Ali Marashian, Luke Gessler, Alexis Palmer, Katharina von der Wense
2024 J jnl
The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification.
CoRR
Minh Duc Bui, Katharina von der Wense
2024 — conf
Zero-Shot vs. Translation-Based Cross-Lingual Transfer: The Case of Lexical Gaps.
NAACL (Short Papers)
Abteen Ebrahimi, Katharina von der Wense
2023 J jnl
Emerging Challenges in Personalized Medicine: Assessing Demographic Effects on Biomedical Question Answering Systems.
CoRR
Sagi Shaier, Kevin Bennett, Lawrence Hunter, Katharina von der Wense
2023 A* conf
On the Automatic Generation and Simplification of Children's Stories.
EMNLP
Maria R. Valentini, Jennifer Weber, Jesus Salcido, Téa Wright, Eliana Colunga, Katharina von der Wense
2023 J jnl
Who Are All The Stochastic Parrots Imitating? They Should Tell Us!
CoRR
Sagi Shaier, Lawrence E. Hunter, Katharina von der Wense