SPP 2556:  Robust Assessment & Safe Applicability of Language Modeling: Foundations for a New Field of Language Science & Technology (LaSTing)

• Subject Area: Social and Behavioural Sciences ; Humanities ; Computer Science, Systems and Electrical Engineering ; Medicine
• Term: since 2026
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 560179209

While modern language technology increasingly permeates many areas of applications, much of its input-output behavior and its inner mechanics remains unknown. As a result, recent years have seen a newly emerging field of interdisciplinary and methodologically diverse work at the interface between the cognitive language sciences (broadly construed) and language technology (focused on neural language models, but not exclusively). However, many foundational and methodological issues remain unclear. The overarching goal of this Priority Programme is therefore to channel cross-disciplinary efforts dedicated to the understanding, testing and safe application of modern language technology (with a focus on language modeling). The Priority Programme LaSTing addresses researchers in the interdisciplinary field of the cognitive and computational language sciences (including classical disciplines such as linguistics, psychology, neuroscience, computational linguistics, artificial intelligence, philosophy, computer science and others) who seek to advance our understanding of language modeling from a theoretical or empirical point of view, or use modern language technology as a tool for innovative theoretical and empirical research in the cognitive language sciences. Individual projects are expected to relate to at least one of the Priority Area’s core issues, which are robust assessment, safe applicability and foundational questions (as detailed in the following). The Priority Programme especially encourages contributions that seek to address these core issues by bringing to bear concepts and methods from the theoretical/empirical language sciences.

• DFG Programme: Priority Programmes
• International Connection: Italy, Netherlands, United Kingdom, USA

Projects

• A multidimensional adaptive test for the psychometric assessment of LLM capabilities (Applicant Günther, Fritz )
• A Resource Efficient Cross-linguistic Approach to Figurative Meaning Assessment in LLMs (Applicant Berger, Maria )
• Attention in Large Language Models: Linguistic Grounding, Cognitive Modeling, and Social Application (Applicants Gotzner, Nicole ;  Musslick, Sebastian )
• Coordination Funds (Applicant Franke, Michael )
• Evaluating, Explaining, and Enabling Ethical Multi-Agent Systems of Large Language Models (E4-MALM) (Applicants Lauscher, Anne ;  Lee, Jae Hee )
• Gesture-Informed Language Models: Evaluating Multimodal Discourse Processing in LLMs and Humans (Applicant Yung, Frances )
• Interpretable Surprisal: Language Models Between Linguistic Structure and Neural Evidence (Applicants Lopopolo, Alessandro ;  Rabovsky, Milena )
• KIND-LM: Cognitively-inspired interaction dynamics for sample-efficient language modeling (Applicants Beinborn, Lisa ;  Mani, Nivedita )
• Learning linguistic inferences and their alternatives (Applicants Romoli, Jacopo ;  Zinova, Yulia )
• Limits and Biases in Machine and Human Language and its Learning (Applicants Alexiadou, Artemis ;  Sauerland, Uli )
• LLADIGA: Learning Language with Dialogue Games (Applicant Schlangen, David )
• Moral Hallucinations in Large Language Models — Their Argumentative Structure and Ethical Implications (Applicants Hautli-Janisz, Annette ;  Reinhardt, Karoline )
• Propositional Attitudes in Large Language Models (PALLM) (Applicant Pasternak, Ph.D., Robert )
• Relating Probabilities of Words to Probabilities of Worlds (Applicant Papay, Sean )
• Structural generalization in transformer-based LLMs (Applicants Hahn, Michael ;  Koller, Alexander )
• Systemic Robustness Assessments of Language Models for Cross-Linguistic Research using Formally Related Structures (FORESTS) (Applicants Hartmann, Jutta M. ;  Himmelreich, Anke ;  Zarrieß, Sina )
• The evaluation of empathy-related linguistic performance in large language models: Comparing surprisal values for next-word predictions in human EEG and LLMs. (Applicant Werning, Markus )
• The pragmatic test: how humans and LLMs decode presupposed meaning (Applicants Bade, Nadine ;  Butt, Miriam )
• The Status of Linguistic Constraints in Neural Language Models (Applicant Hinrichs, Erhard W. )
• Understanding the Cross-Linguistic Brain Basis of Sentence Processing through Interpretable Language Technology (Applicant Meyer, Lars )
• Unreal engines — Understanding language models through resource-optimal analysis: Implicit Bayesian pragmatic reasoning & emergent causal world models (Applicant Franke, Michael )

• Spokesperson: Professor Dr. Michael Franke