23.03.2026
MCML at EACL 2026
13 Accepted Papers (9 Main, and 4 Findings)
19th Conference of the European Chapter of the Association for Computational Linguistics, Rabat, Morocco, Mar 24-29, 2026
We are happy to announce that MCML researchers have contributed a total of 13 papers to EACL 2026: 9 Main, and 4 Finding papers. Congrats to our researchers!
Main Track (9 papers)
S. Ball • F. Kreuter • N. Panickssery
Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
P. H. L. de Araujo • M. A. Hedderich • A. Modarressi • H. Schütze • B. Roth
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
A. Karamolegkou • A. Borah • E. Cho • S. R. Choudhury • M. Galletti • P. Gupta • O. Ignat • P. Kargupta • N. Kotonya • H. Lamba • S.-J. Lee • A. Mangla • I. Mondal • F. Z. Moudakir • D. Nazar • P. Nemkova • D. Pisarevskaya • N. Rizwan • N. Sabri • K. Samway • D. Stammbach • A. Steinberg Schulten • D. Tomás • S. R. Wilson • B. Yi • J. H. Zhu • A. Zubiaga • A. Søgaard • A. Fraser • Z. Jin • R. Mihalcea • J. R. Tetreault • D. Dementieva
NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
F. Körner • M. Müller-Eberstein • A. Korhonen • B. Plank
When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
B. Ma • Y. Cao • I. Sen • A.-C. Haensch • F. Kreuter • B. Plank • D. Hershcovich
Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
J. Orth • P. Mondorf • B. Plank
If Probable, Then Acceptable? Understanding Conditional Acceptability Judgments in Large Language Models.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
If Probable, Then Acceptable? Understanding Conditional Acceptability Judgments in Large Language Models.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
S. Okabe • D. Zelo • A. Fraser
Optical Character Recognition for the International Phonetic Alphabet.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Optical Character Recognition for the International Phonetic Alphabet.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
A. Säuberli • D. Jepifanova • D. Frassinelli • B. Plank
Controlling Reading Ease with Gaze-Guided Text Generation.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Controlling Reading Ease with Gaze-Guided Text Generation.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
T. Zehle • T. Heiß • M. Schlager • M. Aßenmacher • M. Feurer
promptolution: A Unified, Modular Framework for Prompt Optimization.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
promptolution: A Unified, Modular Framework for Prompt Optimization.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Findings Track (4 papers)
L. Christ • S. Amiriparian
Training-Free Text Emotion Tagging via LLM-Based Best-Worst Scaling.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Training-Free Text Emotion Tagging via LLM-Based Best-Worst Scaling.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Y. Liu • Y. Ma • Y. Lu • S. Chen • Z. Ding • V. Tresp
Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
T. Zehle • M. Aßenmacher
Can Calibration of Positional Encodings Enhance Long Context Utilization?
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Can Calibration of Positional Encodings Enhance Long Context Utilization?
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
R. Zhao • Y. Liu • H. Schütze • M. A. Hedderich
A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Related
08.07.2026
How Autonomous Systems Learn to Understand Their Environment
The team at the startup SE3 Labs has developed a spatial AI technology that uses images, videos, and map data to create realistic 3D models.
08.07.2026
MCML Junior Member Sarah Ball Receives Outstanding Position Paper Award at ICML 2026
MCML Junior Member Sarah Ball and her co-author Phil Hackemann received the Outstanding Position Paper Award at ICML 2026 this week in Seoul.
07.07.2026
Michael Hedderich Featured in the Deutschlandfunk
Michael Hedderich discusses how Small Language Models can make AI more efficient, sustainable, and accessible in Deutschlandfunk.
