02.11.2025

MCML at EMNLP 2025

37 Accepted Papers (17 Main, 13 Findings, and 7 Workshops)

Conference on Empirical Methods in Natural Language Processing, Suzhou, China, Nov 04-09, 2025

We are happy to announce that MCML researchers have contributed a total of 37 papers to EMNLP 2025: 17 Main, 13 Findings, and 7 Workshop papers. Congrats to our researchers!

Main Track (17 papers)

J. O. Alabi • M. A. Hedderich • D. I. Adelani • D. Klakow
Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

L. Bertolazzi • P. Mondorf • B. Plank • R. Bernardi
The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

B. Chen • Y. J. Liu • A. Korhonen • B. Plank
Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

Y. Du • P. Mondorf • S. Casola • Y. Yao • R. Litschko • B. Plank
Reason to Rote: Rethinking Memorization in Reasoning.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

F. Ghorbanpour • D. Dementieva • A. Fraser
Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

P. Hong • B. Chen • S. Peng • M.-C. de Marneffe • B. Plank
LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

S. M. Lo • S. Casola • E. Sezerer • V. Basile • F. Sansonetti • A. Uva • D. Bernardi
PERSEVAL: A Framework for Perspectivist Classification Evaluation.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. PDF

Y. Liu • R. Chen • L. Hirlimann • A. D. Hakimi • M. Wang • A. H. Kargaran • S. Rothe • F. Yvon • H. Schütze
On Relation-Specific Neurons in Large Language Models.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

H. Luo • Q. Cheng • D. Matos • H. K. Gadi • Y. Zhang • L. Liu • Y. Wang • N. Zeller • D. Cremers • L. Meng
TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

N. Nikeghbal • A. H. Kargaran • J. Diesner
CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

Y. Shen • W. Lai • S. Wang • G. Gao • K. Luo • A. Fraser • M. Sun
From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

Z. S. Taghavi • A. Modarressi • Y. Ma • H. Schütze
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

A. Testoni • B. Plank • R. Fernández
RACQUET: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

M. Wang • S. Chen • K. Kersting • V. Tresp • Y. Ma
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available.

M. Wang • L. Lange • H. Adel • Y. Ma • J. Strötgen • H. Schütze
Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

C. Wu • B. Ma • Y. Liu • Z. Zhang • N. Deng • Y. Li • B. Chen • Y. Zhang • Y. Xue • B. Plank
M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

Y. Zhang • C. Lin • S. Tang • H. Chen • S. Zhou • Y. Ma • V. Tresp
SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

Findings Track (13 papers)

H. Chen • S. Szyller • W. Xu • N. Himayat
Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

D. Dementieva • N. Babakov • A. Fraser
EmoBench-UA: A Benchmark Dataset for Emotion Detection in Ukrainian.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

Y. Ding • E. Garces Arias • M. Li • J. Rodemann • M. Aßenmacher • D. Chen • G. Fan • C. Heumann • C. Zhang
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

F. Eichin • C. Schuster • G. Groh • M. A. Hedderich
Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

R. Litschko • V. Blaschke • D. Burkhardt • B. Plank • D. Frassinelli
Make Every Letter Count: Building Dialect Variation Dictionaries from Monolingual Corpora.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

Y. Liu • M. Wang • A. H. Kargaran • F. Körner • E. Nie • B. Plank • F. Yvon • H. Schütze
Tracing Multilingual Factual Knowledge Acquisition in Pretraining.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv GitHub

E. Nie • H. Schmid • H. Schütze
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

C. Wu • Y. Cai • Y. Liu • P. Zhu • Y. Xue • Z. Gong • J. Hirschberg • B. Ma
Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

A. Wang • D. Shu • Y. Wang • Y. Ma • M. Du
Improving LLM Reasoning through Interpretable Role-Playing Steering.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

R. Zhao • B. Chen • B. Plank • M. A. Hedderich
MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

L. Zuo • P. Hong • O. Kraus • B. Plank • R. Litschko
Evaluating Large Language Models for Cross-Lingual Retrieval.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

R. Zhao • A. Köksal • A. Modarressi • M. A. Hedderich • H. Schütze
Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

S. Zhou • S. Peng • S. Luebke • J. Haßler • M. Haim • S. M. Mohammad • B. Plank
What Media Frames Reveal About Stance: A Dataset and Study about Memes in Climate Change Discourse.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

Workshops (7 papers)

S. Eckman • B. Ma • C. Kern • R. Chew • B. Plank • F. Kreuter
Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication.
NLPerspectives @EMNLP 2025 - 4th Workshop on Perspectivist Approaches to NLP at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

E. Garces Arias • J. Rodemann • C. Heumann
The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models.
UncertaiNLP @EMNLP 2025 - 2nd Workshop on Uncertainty-Aware NLP at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

E. Leonardelli • S. Casola • S. Peng • G. Rizzi • V. Basile • E. Fersini • D. Frassinelli • H. Jang • M. Pavlovic • B. Plank • M. Poesio
LeWiDi-2025 at NLPerspectives: The Third Edition of the Learning with Disagreements Shared Task.
LeWiDi @EMNLP 2025 - Learning with Disagreements Track at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

C. Ma • Y. Liu • H. Ye • H. Schütze
Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts.
MRL @EMNLP 2025 - 5th Multilingual Representation Learning Workshop at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

P. Mondorf • M. Wang • S. Gerstner • A. D. Hakimi • Y. Liu • L. Veloso • S. Zhou • H. Schütze • B. Plank
BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods.
BlackboxNLP @EMNLP 2025 - 8th Workshop on Analyzing and Interpreting Neural Networks for NLP at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv

S. Okabe • D. Dementieva • M. Di Marco • L. Edman • K. Hämmerl • M. Měškank • A. Hendrichowa • A. Fraser
Findings of the WMT 2025 Shared Task LLMs with Limited Resources for Slavic Languages: MT and QA.
WMT @EMNLP 2025 - 10th Conference on Machine Translation at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. PDF

H. Ye • A. Wisiorek • A. Maronikolakis • Ö. Alaçam • H. Schütze
A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities.
MRL @EMNLP 2025 - 5th Multilingual Representation Learning Workshop at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available. arXiv