Jennifer Haase

Jennifer Haase, Sebastian Pokutta

As large language models (LLMs) transition from static tools to fully agentic systems, their potential for transforming social science research has become increasingly evident. This paper introduces a structured framework for understanding the diverse applications of LLM-based agents, ranging from simple data processors to complex, multi-agent systems capable of simulating emergent social dynamics. By mapping this developmental continuum across six levels, the paper clarifies the technical and methodological boundaries between different agentic architectures, providing a comprehensive overview of current capabilities and future potential. It highlights how lower-tier systems streamline conventional tasks like text classification and data annotation, while higher-tier systems enable novel forms of inquiry, including the study of group dynamics, norm formation, and large-scale social processes. However, these advancements also introduce significant challenges, including issues of reproducibility, ethical oversight, and the risk of emergent biases. The paper critically examines these concerns, emphasizing the need for robust validation protocols, interdisciplinary collaboration, and standardized evaluation metrics. It argues that while LLM-based agents hold transformative potential for the social sciences, realizing this promise will require careful, context-sensitive deployment and ongoing methodological refinement. The paper concludes with a call for future research that balances technical innovation with ethical responsibility, encouraging the development of agentic systems that not only replicate but also extend the frontiers of social science, offering new insights into the complexities of human behavior.

Jana Gonnermann-Müller, Jennifer Haase, Nicolas Leins et al.

Large Language Models (LLMs) acting as artificial agents offer the potential for scalable behavioral research, yet their validity depends on whether LLMs can maintain stable personas across extended conversations. We address this point using a dual-assessment framework measuring both self-reported characteristics and observer-rated persona expression. Across two experiments testing four persona conditions (default, high, moderate, and low ADHD presentations), seven LLMs, and three semantically equivalent persona prompts, we examine between-conversation stability (3,473 conversations) and within-conversation stability (1,370 conversations and 18 turns). Self-reports remain highly stable both between and within conversations. However, observer ratings reveal a tendency for persona expressions to decline during extended conversations. These findings suggest that persona-instructed LLMs produce stable, persona-aligned self-reports, an important prerequisite for behavioral research, while identifying this regression tendency as a boundary condition for multi-agent social simulation.

Jennifer Haase, Paul H. P. Hanel

A widespread view is that Artificial Intelligence cannot be creative. We tested this assumption by comparing human-generated ideas with those generated by six Generative Artificial Intelligence (GAI) chatbots: $alpa.\!ai$, $Copy.\!ai$, ChatGPT (versions 3 and 4), $Studio.\!ai$, and YouChat. Humans and a specifically trained AI independently assessed the quality and quantity of ideas. We found no qualitative difference between AI and human-generated creativity, although there are differences in how ideas are generated. Interestingly, 9.4 percent of humans were more creative than the most creative GAI, GPT-4. Our findings suggest that GAIs are valuable assistants in the creative process. Continued research and development of GAI in creative tasks is crucial to fully understand this technology's potential benefits and drawbacks in shaping the future of creativity. Finally, we discuss the question of whether GAIs are capable of being truly creative.

Jana Gonnermann-Müller, Jennifer Haase, Konstantin Fackeldey et al.

The increasing heterogeneity of student populations poses significant challenges for teachers, particularly in mathematics education, where cognitive, motivational, and emotional differences strongly influence learning outcomes. While AI-driven personalization tools have emerged, most remain performance-focused, offering limited support for teachers and neglecting broader pedagogical needs. This paper presents the FACET framework, a teacher-facing, large language model (LLM)-based multi-agent system designed to generate individualized classroom materials that integrate both cognitive and motivational dimensions of learner profiles. The framework comprises three specialized agents: (1) learner agents that simulate diverse profiles incorporating topic proficiency and intrinsic motivation, (2) a teacher agent that adapts instructional content according to didactical principles, and (3) an evaluator agent that provides automated quality assurance. We tested the system using authentic grade 8 mathematics curriculum content and evaluated its feasibility through a) automated agent-based assessment of output quality and b) exploratory feedback from K-12 in-service teachers. Results from ten internal evaluations highlighted high stability and alignment between generated materials and learner profiles, and teacher feedback particularly highlighted structure and suitability of tasks. The findings demonstrate the potential of multi-agent LLM architectures to provide scalable, context-aware personalization in heterogeneous classroom settings, and outline directions for extending the framework to richer learner profiles and real-world classroom trials.

Jana Gonnermann-Müller, Jennifer Haase, Nicolas Leins et al.

Classrooms are becoming increasingly heterogeneous, comprising learners with diverse performance and motivation levels, language proficiencies, and learning differences such as dyslexia and ADHD. While teachers recognize the need for differentiated instruction, growing workloads create substantial barriers, making differentiated instruction an ideal that is often unrealized in practice. Current AI educational tools, which promise differentiated materials, are predominantly student-facing and performance-centric, ignoring other aspects that shape learning outcomes. We introduce FACET, a teacher-facing multi-agent framework designed to address these gaps by supporting differentiation that accounts for motivation, performance, and learning differences. Developed with educational stakeholders from the outset, the framework coordinates four specialized agents, including learner simulation, diagnostic assessment, material generation, and evaluation within a teacher-in-the-loop design. School principals (N = 30) shaped system requirements through participatory workshops, while in-service K-12 teachers (N = 70) evaluated material quality. Mixed-methods evaluation demonstrates strong perceived value for inclusive differentiation. Practitioners emphasized both the urgent need arising from classroom heterogeneity and the importance of maintaining pedagogical autonomy as a prerequisite for adoption. We discuss implications for future school deployment and outline partnerships for longitudinal classroom implementation.

Jennifer Haase, Jana Gonnermann-Müller, Paul H. P. Hanel et al.

How much of LLM output variance is explained by prompts versus model choice versus stochasticity through sampling? We answer this by evaluating 12 LLMs on 10 creativity prompts with 100 samples each (N = 12,000). For output quality (originality), prompts explain 36.43% of variance, comparable to model choice (40.94%). But for output quantity (fluency), model choice (51.25%) and within-LLM variance (33.70%) dominate, with prompts explaining only 4.22%. Prompts are powerful levers for steering output quality, but given the substantial within-LLM variance (10-34%), single-sample evaluations risk conflating sampling noise with genuine prompt or model effects.

Paul H. P. Hanel, Gabriel Lins de Holanda Coelho, Jennifer Haase

The rapid expansion of high-speed internet has led to the emergence of new digital jobs, such as digital influencers, fitness models, and adult models who share content on subscription-based social media platforms. Across two experiments involving 1,002 participants, we combined theories from social psychology and information systems to investigate how digital jobs are perceived compared to matched established jobs, and predictors of attitudes toward those jobs (e.g., symbolic threat, contact, perceived usefulness). We found that individuals in digital professions were perceived as less favorably and less hard-working than those in matched established jobs. Digital jobs were also regarded as more threatening to societal values and less useful. The relation between job type and attitudes toward these jobs was partially mediated by contact with people working in these jobs, perceived usefulness, perception of hard work, and symbolic threat. These effects were consistent across both experiments, and various moderators: openness to new experiences, attitudes toward digitalization, political orientation, and age. Among the nine jobs examined, lecturers were perceived as most positive, while adult models were viewed as least positive. Overall, our findings demonstrate that integrating theories from social psychology and information systems can enhance our understanding of how attitudes are formed.

Jana Gonnermann-Müller, Jennifer Haase, Nicolas Leins et al.

Student simulation with Large language models (LLMs) offers a scalable alternative for educational research and teacher training. Yet, its validity depends on whether models maintain stable personas across extended interactions. We test this prerequisite using a dual-assessment framework measuring self-reported characteristics and observer-rated behavioral expressions. Across two experiments testing four clinically-grounded ADHD persona conditions, five LLMs, and three prompt designs, we quantify between-conversation stability (N=4,968) and within-conversation stability (N=3,952 across 9 turns). Self-reported characteristics remain stable for high intensities, constituting a necessary prerequisite for valid behavioral simulation. Observer-rated behavioral expression reveals selective instability: within-conversation drift occurs in unscripted dialog for high and moderate ADHD personas. Scripted interactions with explicit task prompts eliminate this drift entirely. Stable, persona-aligned simulated learners benefit from a structured interaction design to maintain behavioral coherence, which holds significant implications for teacher training, adaptive tutoring, and any application requiring sustained, path-dependent learner interactions.

Jennifer Haase, Paul H. P. Hanel, Sebastian Pokutta

Following the widespread adoption of ChatGPT in early 2023, numerous studies reported that large language models (LLMs) can match or even surpass human performance in creative tasks. However, it remains unclear whether LLMs have become more creative over time, and how consistent their creative output is. In this study, we evaluated 14 widely used LLMs -- including GPT-4, Claude, Llama, Grok, Mistral, and DeepSeek -- across two validated creativity assessments: the Divergent Association Task (DAT) and the Alternative Uses Task (AUT). Contrary to expectations, we found no evidence of increased creative performance over the past 18-24 months, with GPT-4 performing worse than in previous studies. For the more widely used AUT, all models performed on average better than the average human, with GPT-4o and o3-mini performing best. However, only 0.28% of LLM-generated responses reached the top 10% of human creativity benchmarks. Beyond inter-model differences, we document substantial intra-model variability: the same LLM, given the same prompt, can produce outputs ranging from below-average to original. This variability has important implications for both creativity research and practical applications. Ignoring such variability risks misjudging the creative potential of LLMs, either inflating or underestimating their capabilities. The choice of prompts affected LLMs differently. Our findings underscore the need for more nuanced evaluation frameworks and highlight the importance of model selection, prompt design, and repeated assessment when using Generative AI (GenAI) tools in creative contexts.

Jennifer Haase, Paul H. P. Hanel, Sebastian Pokutta

This paper introduces S-DAT (Synthetic-Divergent Association Task), a scalable, multilingual framework for automated assessment of divergent thinking (DT) -a core component of human creativity. Traditional creativity assessments are often labor-intensive, language-specific, and reliant on subjective human ratings, limiting their scalability and cross-cultural applicability. In contrast, S-DAT leverages large language models and advanced multilingual embeddings to compute semantic distance -- a language-agnostic proxy for DT. We evaluate S-DAT across eleven diverse languages, including English, Spanish, German, Russian, Hindi, and Japanese (Kanji, Hiragana, Katakana), demonstrating robust and consistent scoring across linguistic contexts. Unlike prior DAT approaches, the S-DAT shows convergent validity with other DT measures and correct discriminant validity with convergent thinking. This cross-linguistic flexibility allows for more inclusive, global-scale creativity research, addressing key limitations of earlier approaches. S-DAT provides a powerful tool for fairer, more comprehensive evaluation of cognitive flexibility in diverse populations and can be freely assessed online: https://sdat.iol.zib.de/.

Jennifer Haase, Finn Klessascheck, Jan Mendling et al.

Large language models (LLMs) have become increasingly embedded in organizational workflows. This has raised concerns over their energy consumption, financial costs, and data sovereignty. While performance benchmarks often celebrate cutting-edge models, real-world deployment decisions require a broader perspective: when is a smaller, locally deployable model "good enough"? This study offers an empirical answer by evaluating eleven proprietary and open-weight LLMs across ten everyday occupational tasks, including summarizing texts, generating schedules, and drafting emails and proposals. Using a dual-LLM-based evaluation framework, we automated task execution and standardized evaluation across ten criteria related to output quality, factual accuracy, and ethical responsibility. Results show that GPT-4o delivers consistently superior performance but at a significantly higher cost and environmental footprint. Notably, smaller models like Gemma-3 and Phi-4 achieved strong and reliable results on most tasks, suggesting their viability in contexts requiring cost-efficiency, local deployment, or privacy. A cluster analysis revealed three model groups -- premium all-rounders, competent generalists, and limited but safe performers -- highlighting trade-offs between quality, control, and sustainability. Significantly, task type influenced model effectiveness: conceptual tasks challenged most models, while aggregation and transformation tasks yielded better performances. We argue for a shift from performance-maximizing benchmarks to task- and context-aware sufficiency assessments that better reflect organizational priorities. Our approach contributes a scalable method to evaluate AI models through a sustainability lens and offers actionable guidance for responsible LLM deployment in practice.