Research Group – Data Science & Language Technologies
Publications
2026
Pluralistic AI Alignment: A Cross-Cultural Pilot Survey. K Alavi, L Flek, F Mai. Second Workshop on Language Models for Underserved Communities (LM4UC).
Read more
On the Limitations of Language-targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning. S Kurz, JJ Chen, L Flek, Z Zhao. Transactions of the Association for Computational Linguistics 14, 167-192.
Read more
PERSPECTRA: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments. S Nie, K Omoomi, L Flek, Z Zhao, C Welch. arXiv preprint. arXiv:2602.08716.
Read more
Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models C Nickel, L Schrewe, F Mai, L Flek.
Read more
Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents MHA Monfared, L Flek, A Karimi.
Read more
Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi S Fatimah, A Sen, S Falk, F Mai, L Flek, NK Corrêa. arXiv preprint arXiv:2603.03508.
Read more
2025
Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight GPT in Astronomy Knowledge Extraction. S Rawat, L Flek, A Karimi.
Read more
TARGAMA: A Novel Benchmark Dataset and Framework for Translating Dialectal Arabic to English with Generative Language Models. B Abdou, H Elsafty, F Aldabbas, M Pielka, R Sifa, L Flek.
Read more
More Agents Helps but Adversarial Robustness Gap Persists. K Alavi, Z Yeltay, L Flek, A Karimi. arXiv preprint arXiv:2511.07112.
Read more
MiniFool-Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks. L Flek, O Janik, PA Jung, A Karimi, Timo Saala, A Schmidt, M Schott, P Soldin, M Thiesmeyer, C Wiebusch, U Willemsen. arXiv preprint arXiv:2511.01352.
Read more
The Practical Impacts of Theoretical Constructs on Empathy Modeling. A Lahnala, C Welch, D Jurgens, L Flek
Read more
CINEMETRIC: A Framework for Multi-Perspective Evaluation of Conversational Agents using Human-AI Collaboration. VS Javadi, ZU Abedin, L Flek
Read more
IKnow: Instruction-Knowledge-Aware Continual Pretraining for Effective Domain Adaptation. T Zhang, F Mai, L Flek. arXiv preprint arXiv:2510.20377.
Read more
Proceedings of the 18th International Natural Language Generation Conference: System Demonstrations. L Flek, S Narayan, J Pei.
Read more
Disparities in Multilingual LLM-Based Healthcare Q&A. IB Schlicht, B Sayin, Z Zhao, FM Labonté, C Barbera, M Viviani, P Rosso, L Flek. arXiv e-prints, arXiv: 2510.17476.
Read more
Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics at ECML PKDD 2025. T Saala, L Flek, A Karimi, PA Jung, A Schmidt, P Soldin, D Stefanopoulos, A Voskou, U Willemsen, C Wiebusch, M Schott.
Read more
EDAudio: Easy Data Augmentation for Dialectal Audio. L Fischbach, A Karimi, A Lameli, L Flek.
Read more
Funzac at CoMeDi Shared Task: Modeling annotator disagreement from word-in-context perspectives. Olufunke O Sarumi, Charles Welch, Lucie Flek, Jörg Schlötterer. arXiv preprint arXiv:2501.14617.
Read more
ISCA: A Framework for Interview-Style Conversational Agents. C Welch, A Lahnala, V Varadarajan, L Flek, R Mihalcea, JL Boyd, J Sedoc. arXiv preprint arXiv:2508.14344.
Read more
Survey-to-Behavior: Downstream Alignment of Human Values in LLMs via Survey Questions. S Nie, F Mai, D KaczĂŠr, C Welch, Z Zhao, L Flek. arXiv preprint arXiv:2508.11414.
Read more
In-Training Defenses against Emergent Misalignment in Language Models. D Kaczér, M Jørgenvåg, C Vetter, L Flek, F Mai. arXiv preprint arXiv:2508.06249.
Read more
Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversion. L Fischbach, A Karimi, C Kleen, A Lameli, L Flek. arXiv preprint arXiv:2507.03641.
Read more
Multi-Hop Reasoning for Question Answering with Hyperbolic Representations. S Welz, L Flek, A Karimi. arXiv preprint arXiv:2507.03612.
Read more
CAISA at SemEval-2025 Task 7: Multilingual and Cross-lingual Fact-Checked Claim Retrieval. M Haroon, S Ashraf, I Baris, L Flek. Proceedings of the 19th International Workshop on Semantic Evaluation.
Read more
Explainable Hallucination through Natural Language Inference Mapping. WF Chen, Z Zhao, A Karimi, L Flek. Findings of the Association for Computational Linguistics: ACL 2025, 1888-1896.
Read more
Unifying the Extremes: Developing a Unified Model for Detecting and Predicting Extremist Traits and Radicalization. A Lahnala, V Varadarajan, L Flek, HA Schwartz, RL Boyd.
Read more
Detection of Medical Conspiracy Theories with Limited Resources: Using Data from Prior Epidemics and LLMs. IB Schlicht, D Korenčić, B Chulvi, L Flek, P Rosso.
Read more
Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models. Mehdi Ali, Manuel Brack, Max Lübbering, Elias Wendt, Abbas Goher Khan, Richard Rutmann, Alex Jude, Maurice Kraus, Alexander Arno Weber, David Kaczér, Florian Mai, Lucie Flek, Rafet Sifa, Nicolas Flores-Herr, Joachim Köhler, Patrick Schramowski, Michael Fromm, Kristian Kersting.
Read more
Detection of Medical Conspiracy Theories with Limited Resources: Using Data from Prior Epidemics and LLMs. IB Schlicht, D Korenčić, B Chulvi, L Flek, P Rosso.
Read more
Does Preprocessing Matter? An Analysis of Acoustic Feature Importance in Deep Learning for Dialect Classification. L Fischbach, C Kleen, L Flek, A Lameli. Proceedings of the Joint 25th Nordic Conference on Computational Linguistics…
Read more.
Superalignment with Dynamic Human Values. F Mai, D Kaczér, NK Corrêa, L Flek. arXiv preprint arXiv:2503.13621.
Read more
The Muddy Waters of Modeling Empathy in Language: The Practical Impacts of Theoretical Constructs. A Lahnala, C Welch, D Jurgens, L Flek. arXiv preprint arXiv:2501.14981 (2025).
Read more
Do LLMs Provide Consistent Answers to Health-Related Questions across Languages? IB Schlicht, Z Zhao, B Sayin, L Flek, P Rosso. arXiv preprint arXiv:2501.14719 (2025).
Read more
ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving. Abedin, Zain Ul, et al.. arXiv preprint arXiv:2501.08203 (2025).
Read more
Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations. T Saala, L Flek, A Jung, A Karimi, A Schmidt, M Schott, P Soldin, …arXiv preprint arXiv:2501.05588 (2025).
Read more
Exploring Robustness of LLMs to Sociodemographically-Conditioned Paraphrasing. Arora, Pulkit, Akbar Karimi, and Lucie Flek. arXiv preprint. arXiv:2501.08276 (2025). Read more
Unifying the Extremes: Developing a Unified Model for Detecting and Predicting Extremist Traits and Radicalization. A Lahnala, V Varadarajan, L Flek, HA Schwartz, RL Boyd. arXiv preprint. arXiv:2501.04820 (2025).
Read more
Exploring Robustness of Multilingual LLMs on Real-World Noisy Data. Aliakbarzadeh, Amirhossein, Lucie Flek, and Akbar Karimi. arXiv preprint. arXiv:2501.08322 (2025).
Read more
MultiProp Framework: Ensemble Models for Enhanced Cross-Lingual Propaganda Detection in Social Media and News using Data Augmentation, Text Segmentation, and Meta-Learning. F Aldabbas, S Ashraf, R Sifa, L Flek. Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script, 7-22.
Read more
A Comparison of Data Augmentation Techniques for Text Classification. Peyman Hassani Jalilian, Akbar Karimi.
2024
Explaining GPT-4’s Schema of Depression Using Machine Behavior Analysis. AV Ganesan, V Varadarajan, YK Lal, VC Eijsbroek, K Kjell, ONE Kjell, … arXiv preprint. arXiv:2411.13800 (2024).
Read more
How large language models can reshape collective intelligence. Burton, Jason W and Lopez-Lopez, Ezequiel and Hechtlinger, Shahar and Rahwan, Zoe and Aeschbach, Samuel and Bakker, Michiel A and Becker, Joshua A and Berditchevskaia, Aleks and Berger, Julian and Brinkmann, Levin and others. Nature Human Behaviour 2024.
Read more
Probing the Robustness of Theory of Mind in Large Language Models. C Nickel, L Schrewe, L Flek. arXiv preprint. arXiv:2410.06271 (2024).
Read more
Do Multilingual Large Language Models Mitigate Stereotype Bias? Nie, Shangrui and Fromm, Michael and Welch, Charles and Görge, Rebekka and Karimi, Akbar and Plepi, Joan and Mowmita, Nazia Afsan and Flores-Herr, Nicolas and Ali, Mehdi and Flek, Lucie. C3NLP 2024
Perspective Taking through Generating Responses to Conflict Situations. Plepi, Joan and Welch, Charles and Flek, Lucie. ACL Findings 2024.
Unveiling Information Through Narrative In Conversational Information Seeking. Sadiri Javadi, Vahid and Trippas, Johanne R and Flek, Lucie. CUI 2024.
Read more
Pitfalls of Conversational LLMs on News Debiasing. Schlicht, Ipek Baris and Altiok, Defne and Taouk, Maryanne and Flek, Lucie. DELITE 2024.
A Perspectivist Corpus of Numbers in Social Judgements. May, Marlon and Flek, Lucie and Welch, Charles. NLPerspectives LREC-COLING 2024.
Corpus Considerations for Annotator Modeling and Scaling. Olufunke O. Sarumi and Béla Neuendorf and Joan Plepi and Lucie Flek and Jörg Schlötterer and Charles Welch. NAACL 2024.
Read more.
Can Stories Help LLMs Reason? Curating Information Space Through Narrative. V Sadiri Javadi, JR Trippas, YK Lal, L Flek. arXiv e-prints, arXiv: 2410.19221 (2024).
Read more
Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation. S Balloccu, Z Kasner, O Plátek, P Schmidtová, K Onderková, M Lango, … Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text …
Read more
Language-specific Calibration for Pruning Multilingual Language Models. S Kurz, Z Zhao, JJ Chen, L Flek. arXiv preprint. arXiv:2408.14398.
Read more
Large Language Models are Human-like Annotators. Marreddy, Mounika and Oota, Subba Reddy and Gupta, Manish and Flek, Lucie. KR 2024.
Harnessing Personalization Methods to Identify and Predict Unreliable Information Spreader Behavior. Ashraf, Shaina and Gruschka, Fabio and Flek, Lucie and Welch, Charles. WOAH 2024.
EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization. O Sotolar, V Formanek, A Debnath, A Lahnala, C Welch, L Flek. arXiv preprint. arXiv:2406.19071 (2024).
Read more
Archetypes and Entropy: Theory-Driven Extraction of Evidence for Suicide Risk. Varadarajan, Vasudha and Lahnala, Allison and Ganesan, Adithya V. and Dey, Gourab and Mangalik, Siddharth and Bucur, Ana-Maria and Soni, Nikita and Rao, Rajath and Lanning, Kevin and Vallejo, Isabella and Flek, Lucie and Schwartz, H. Andrew and Welch, Charles and Boyd, Ryan L..CLPsych 2024.
Appraisal Framework for Clinical Empathy: A Novel Application to Breaking Bad News Conversations. Lahnala, Allison and Neuendorf, Béla and Thomin, Alexander and Welch, Charles and Stibane, Tina and Flek, Lucie. LREC 2024.
DeFaktS: A Fine-Grained Dataset for Analyzing Disinformation in German Media. Ashraf, Shaina and Bezzaoui, Isabel and Andone, Ionut and Markowetz, Alexander and Fegert, Jonas and Flek, Lucie. LREC 2024.
Reference-guided Style-Consistent Content Transfer. Chen, Wei-Fan and Alshomary, Milad and Stahl, Maja and Al Khatib, Khalid and Stein, Benno and Wachsmuth, Henning. LREC 2024.
Vanishing Boundaries: A Unifying Account of Multidimensional Emotion Dynamics and Alterations in Depression. AM Bucur, TA Koosha, A Cosma, L Flek, SE Thanarajah, F Bernhard, …OSF.
Read more
USDC: A dataset of user stance and dogmatism in long conversations. M Marreddy, SR Oota, VC Chinni, M Gupta, L Flek.
Read more
Proceedings of the 1st Human-Centered Large Language Modeling Workshop. N Soni, L Flek, A Sharma, D Yang, S Hooker, HA Schwartz
Proceedings of the 1st Human-Centered Large Language Modeling Workshop.
Read more
LeadEmpathy: An Expert Annotated German Dataset of Empathy in Written Leadership Communication. Sedefoglu, Didem and Lahnala, Allison and Wagner, Jasmin and Flek, Lucie and Ohly, Sandra. LREC 2024.
2023
Style Locality for Controllable Generation with kNN Language Models. Nawezi, Gilles and Flek, Lucie and Welch, Charles.
Read more.
Personalized Intended and Perceived Sarcasm Detection on Twitter. Plepi, Joan and Buski, Magdalena and Flek, Lucie. cpss 2023.
Read more.
Challenges of GPT-3-Based Conversational Agents for Healthcare. Lechner, Fabian and Lahnala, Allison and Welch, Charles and Flek, Lucie. RANLP 2023.
Read more.
OpinionConv: Conversational Product Search with Grounded Opinions. Sadiri Javadi, Vahid and Potthast, Martin and Flek, Lucie. SIGDIAL 2023.
Read more.
Domain Transfer for Empathy, Distress, and Personality Prediction. Gruschka, Fabio and Lahnala, Allison and Welch, Charles and Flek, Lucie. WASSA 2023. Read more.
Multilingual Detection of Check-Worthy Claims Using World Languages and Adapter Fusion. Schlicht, Ipek Baris and Flek, Lucie and Rosso, Paolo. Read more.
2022
Investigating Paraphrasing-Based Data Augmentation for Task-Oriented Dialogue Systems. Vogel, Liane and Flek, Lucie.
Read more
FACTOID: A New Dataset for Identifying Misinformation Spreaders and Political Bias. Sakketou, Flora and Plepi, Joan and Cervero, Riccardo and Geiss, Henri Jacques and Rosso, Paolo and Flek, Lucie.
Read more.
Refining Diagnosis Paths for Medical Diagnosis based on an Augmented Knowledge Graph. Heilig, Niclas and Kirchhoff, Jan and Stumpe, Florian and Plepi, Joan and Flek, Lucie and Paulheim, Heiko.
Investigating User Radicalization: A Novel Dataset for Identifying Fine-Grained Temporal Shifts in Opinion.Sakketou, Flora and Lahnala, Allison and Vogel, Liane and Flek, Lucie.
Framing in Communication: From Theories to Computation (Dagstuhl Seminar 22131). K Budzynska, C Reed, M Stede, B Stein, H Zhang, K Al-Khatib, L Allein, A Bondarenko, P Cimiano, L Flek, A Frank, I Gurevych, I Habernal, A Hautli-Janisz, Z Kikteva, K Kiljan, C Klamm, M Koszowy, M Oostindie, S Oswald, J Parkinson, M Potthast, A Pramanick, A Rocci, A Simons, S Wassiliki, J Skolimowska, N Slonim, H Wachsmuth.
Read more.
Knowledge Enhanced Reflection Generation for Counseling Dialogues. Shen, Siqi and Perez-Rosas, Veronica and Welch, Charles and Poria, Soujanya and Mihalcea, Rada. ACL 2022.
Read more.
2021
HypMix: Hyperbolic Interpolative Data Augmentation. Sawhney, Ramit and Thakkar, Megh and Agarwal, Shivam and Jin, Di and Yang, Diyi and Flek, Lucie. EMNLP 2021.
Read more.
Perceived and Intended Sarcasm Detection with Graph Attention Networks. Plepi, Joan and Flek, Lucie. Findings 2021.
Read more.
Towards User-Centric Text-to-Text Generation: A Survey. Yang, Diyi and Flek, Lucie.
Read more.
Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning. Sawhney, Ramit and Joshi, Harshit and Shah, Rajiv Ratn and Flek, Lucie. NAACL-HLT 2021.
Read more.