Home | News

01.07.2026

Tiny logo
Teaser image to MCML at ACL 2026

MCML at ACL 2026

38 Accepted Papers (21 Main, 14 Findings, and 3 Workshops)

64th Annual Meeting of the Association for Computational Linguistics, San Diego, CA, USA, Jul 02-07, 2026

We are happy to announce that MCML researchers have contributed a total of 38 papers to ACL 2026: 21 Main, 14 Findings, and 3 Workshop papers. Congrats to our researchers!

Main Track (21 papers)

G. Ahnert • A.-C. Haensch • B. Plank • M. Strohmaier
Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

V. Blaschke • M. Winkler • B. Plank
Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialects.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

C. Chan • Y. Yim • H. Zeng • Z. Zou • X. Cheng • Z. Sun • Z. Deng • K. Chung • Y. Ao • Y. Fan • C. Jiayang • E. Nie • G. Y. Wong • H. Schmid • H. Schütze • S. See • Y. Song
XToM: Exploring the Multilingual Theory of Mind for Large Language Models.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

Y. Ding • M. Li • E. Garces Arias • M. Aßenmacher • C. Heumann • C. Zhang
Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

Y. Liu • X. Xu • E. Nie • Z. Wang • S. Feng • D. Wang • Q. Li • H. Schütze
Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

Y. Liu • J. Yu • M. Wang • Y. Zhang • E. Nie • S. Feng • D. Wang • K. Song • H. Schütze
SAD: A Large-Scale Strategic Argumentative Dialogue Dataset.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

B. Ma • Y. Miyao
The Imperfective Paradox in Large Language Models.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

S. Ostermann • D. Gurgurov • T. Baeumel • M. A. Hedderich • S. Lapuschkin • W. Samek • V. Schmitt
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

A. Sarawgi • E. Garces Arias • C. Zotter
Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

M. Štefánik • T. Mickus • M. Kadlčík • B. Højer • M. Spiegel • R. Vázquez • A. Sinha • J. Kuchař • P. Mondorf • P. Stenetorp
Language Models Learn Universal Representations of Numbers and Here's Why You Should Care.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

L. Veloso • H. Schütze
GKnow: Measuring the Entanglement of Gender Bias and Factual Gender.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

Q. Wang • V. Bach Nguyen • Y. Liu • F. Splitt • N. Feldhus • C. Seifert • H. Schütze • S. Möller • V. Schmitt
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

C. Wu • B. Ma • N. Deng • Y. He • Y. Xue • X. Liu
MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

F. Weeber • V. Neplenbroek • J. Batzner • S. Padó
One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

Z. Wang • X. Xu • Y. Liu • Y. Zhang • P. Lin • S. Feng • X. Yang • D. Wang • H. Schütze
Why Do More Experts Fail? A Theoretical Analysis of Model Merging.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

H. Yu • T. Xu • M. A. Hedderich • W. Hamidouche • S. W. Zamir • D. I. Adelani
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI URL

S. Yan • X. Yang • Z. Huang • E. Nie • Z. Ding • Z. Li • X. Ma • J. Bi • K. Kersting • J. Z. Pan • H. Schütze • V. Tresp • Y. Ma
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

C. Yuan • Z. Zhang • G. Kasneci
Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

S. Yang • Z. Zhang • B. Prenkaj • G. Kasneci
SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

R. Zhao • Y. Liu • L. Altinger • H. Schütze • M. A. Hedderich
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

W. Zhou • B. Ma • A. Friedrich • M. Mesgar
Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

Findings Track (14 papers)

I. Bueno • B. Bühler • P. Stark • T. Fütterer • U. Trautwein • D. Demszky • H. Hill • E. Kasneci
From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

B. Chen • T. Hu • C. Zhang • R. Litschko • A. Korhonen • B. Plank
Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

X. Dong • C. Wu • Y. Wen • Y. Chen • Y. Xue • J. Zhang • W. Xu • B. Ma
FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. DOI

P. Hong • B. Chen • S. Peng • M.-C. de Marneffe • B. Roth • B. Plank
Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

Y. Li • A. Fastowski • E. Zaradoukas • B. Prenkaj • G. Kasneci
Analysing the Safety Pitfalls of Steering Vectors.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

Y. Liu • R. Zhao • H. Schütze • M. A. Hedderich
Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

X. Ma • Y. Ma • C. Lin • S. Yan • J. Bi • Z. Cao • Y. Tian • V. Tresp • H. Schütze
Self-Evolving Multi-Agent Systems via Textual Backpropagation.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

B. Ma • Y. Yao • A.-C. Haensch
Capabilities and Evaluation Biases of Large Language Models in Classical Chinese Poetry Generation: A Case Study on Tang Poetry.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

A. Plum • F. Körner • A.-M. Lutgen • L. Bernardy • F. Philippy • E. Milano • N. Rehlinger • C. Lothritz • T. Ranasinghe • B. Plank • C. Purschke
ltzGLUE: Luxembourgish General Language Understanding Evaluation.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

R. S.-E. Shim • K. Choi • K. Chang • M.-H. Hsu • F. Eichin • Z. Wu • A. Suhr • M. A. Hedderich • D. Harwath • D. R. Mortensen • B. Plank
Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

Z. Wang • Y. Liu • M. Wang • E. Nie • D. Chen • Z. Zhao • S. Feng • D. Wang • X. Yang • Y. Zhang • H. Schütze
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

S. Xu • S. T. Y. S. S • B. Plank
Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

L. Zuo • B. Plank • S. Peng
EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

C. Zhang • H. Wang • Z. Yu • E. Garces Arias • J. Rodemann • Z. Zhang • Q. Li • G. Fan • K. Muandet • C. Heumann
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

Workshops (3 papers)

I. Bueno • L. Hirlimann • E. Kasneci
MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection.
LT-EDI @ACL 2026 - 6th Workshop on Language Technology for Equality, Diversity and Inclusion at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

A. Dikhtiar • A. Viter • B. Karaziia • D. Dementieva • A. Fraser
aba_team at SemEval-2026 Task 1: Plan2joke – Humor Policies for Type-Specific Two-Pass Humor Generation.
SemEval @ACL 2026 - 20th International Workshop on Semantic Evaluation at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI GitHub

Q. Wang • M. Wang • N. Feldhus • S. Ostermann • Y. Cao • H. Schütze • S. Möller • V. Schmitt
Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability.
TrustNLP @ACL 2026 - 6th Workshop on Trustworthy NLP at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. DOI

#research #top-tier-work #bischl #fraser #hedderich #kasneci-enkelejda #kasneci-gjergji #kreuter #plank #schuetze #tresp

Related

Link to Enkelejda Kasneci: The Real Value of AI in Education Is More Time for Humans

17.11.2026

Enkelejda Kasneci: The Real Value of AI in Education Is More Time for Humans

Enkelejda Kasneci explores how AI can provide personalized learning support while keeping human interaction and student agency at the center.

Read more
Link to Digdeep Podcast: Career leaps and comfort zones – what does it take for a successful career, Daniela Gerd tom Markotten?

13.11.2026

Digdeep Podcast: Career Leaps and Comfort Zones – What Does It Take for a Successful Career, Daniela Gerd Tom Markotten?

In the new episode of #digdeep, Daniela Gerd tom Markotten talks about technology, speed and career advancements.

Read more
Link to One Toolbox for Many Kinds of Uncertainty

12.11.2026

One Toolbox for Many Kinds of Uncertainty

MCML researchers introduce probly, a unified Python package for uncertainty-aware machine learning, presented orally at NeurIPS 2026.

Read more
Link to Outstanding Paper Award at EMNLP 2026 for Work on Accent Bias in Audio Language Models

09.11.2026

Outstanding Paper Award at EMNLP 2026 for Work on Accent Bias in Audio Language Models

A paper co-authored by MCML PI Valentin Hofmann on accent bias in audio language models won an Outstanding Paper Award at EMNLP 2026.

Read more
Link to Best Thesis Award for Sohir Maskey

06.11.2026

Best Thesis Award for Sohir Maskey

Former MCML Junior Member Sohir Maskey received the Best Thesis Award of the DFG Priority Programme 2298 for his PhD on graph neural networks.

Read more
Back to Top