arXiv subjects

Jennifer Haase

Publications and source records attributed to Jennifer Haase.

16 recordsLinked to original sources

arXiv2026

LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles

Large language model (LLM)-based student simulation offers a scalable alternative for educational research, teacher training, and learner practice. However, its validity depends on whether LLMs maintain stable personas across and within interactions. We test this using a dual-assessment framework measuring self-reported characteristics and observer-rated behavioral expressions. Across three ICD-11-informed ADHD-related intensity conditions and a default condition, five LLMs, and three prompt designs, we quantify between-conversation (Exp. I; N=$4,962$) and within-conversation stability (Exp. II; N=$3,952$). Experiment I shows that self-reports and observer ratings are more stable at high than moderate intensities across the tested models, prompts, and independent runs. Experiment II shows that self-reports remain stable throughout extended interactions, but observer-rated behavior drifts in unscripted dialog for high- and moderate-intensity personas. Scripted interactions with recurring task-relevant prompts eliminate this drift almost entirely (up to 97\% reduction). Structured interaction design helps simulated learners maintain behavioral stability in sustained, path-dependent interactions.

cs.HC↗

arXiv2026

Prompting Against Persona Drift: Comparing Intervention Timing and Content in LLM-Simulated Conversations

Simulating student personas with large language models (LLMs) enables scalable evaluation of educational systems. However, behavioral drift, a progressive decline in persona consistency, can emerge over extended conversations, limiting the validity of such simulations. We evaluate five prompt-level mechanisms using separate monitoring and intervention pipelines. Across 1,200 28-turn conversations spanning four LLMs and two ADHD persona intensities, we varied when to intervene (static vs. adaptive) and what to inject (reinjection vs. reflective reminder), plus a novel adaptive condition in which a monitor generates behavior-specific instructions. Relative to no intervention, reinjection reduced the modeled rate of LLM-rated drift by 35--38\%, reflective reminders by 22--27\%, and behavior-specific instruction by 87\%. None eliminated drift. We found no evidence that adaptive timing outperformed static scheduling. Monitoring therefore appears more useful for deciding \textit{what} to correct than \textit{when} to intervene, although behavior-specific instruction requires component-level testing.

cs.HC↗

arXiv2026

FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students

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.

cs.HC↗

arXiv2026

Stable Personas: Dual-Assessment of Temporal Stability in LLM-Based Human Simulation

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.

cs.HC↗

arXiv2026

FACET: Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets

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.

cs.HC↗

arXiv2026

Sustainability via LLM Right-sizing

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.

cs.CL↗

arXiv2026

Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research

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.

cs.MA↗

arXiv2026

Simulating Eating Disorder Patients with LLMs: Evaluating Psychological Persona Stability in Multi-Turn Conversations

Large language model (LLM)-based simulations of clinical patients are increasingly used for research and training, yet their validity requires persona stability: coherent maintenance of an assigned psychological profile across and within conversations. We evaluate this prerequisite using eating disorder personas grounded in five published case vignettes, a dual-assessment framework (self-report + independent observer ratings), and validated psychometric instruments (EDE-Q) with known ground-truth scores. Across six LLMs and two experiments (between-conversation stability (Exp. I) and within-conversation stability (Exp. II)), we find that LLMs are paradoxically too stable and too inaccurate: variability is negligible, yet all models systematically overshoot ground-truth severity by 12-30% of the scale range (0.7-1.8 points on a 0-6 scale). The mechanism is selective stereotyping: models differentiate cases on behavioural items (dietary restraint) but maximise cognitive-affective items (body dissatisfaction, weight preoccupation) at ceiling regardless of case severity. Additional conversational context does not improve accuracy; it compounds the overshoot. LLMs can portray severe eating pathology but lack a representation of moderate clinical presentations, a "missing middle".

cs.CY↗

arXiv2026

From Influencers to Lecturers: Understanding Public Attitudes Toward Digital vs. Traditional Jobs

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.

cs.CY↗

arXiv2026

Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks

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.

cs.AI↗

arXiv2025

S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessment

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/.

cs.CL↗

arXiv2025

Towards a Theory on Process Automation Effects

Process automation is a crucial strategy for improving business processes, but little attention has been paid to the effects that automation has once it is operational. This paper addresses this research problem by reviewing the literature on human-automation interaction. Although many of the studies in this field have been conducted in different domains, they provide a foundation for developing propositions about process automation effects. Our analysis focuses on how humans perceive automation technology when working within a process, allowing us to propose an effective engagement model between technology, process participants, process managers, and software developers. This paper offers insights and recommendations that can help organizations optimize their use of process automation. We further derive novel research questions for a discourse within the process automation community.

cs.SE↗

arXiv2025

Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability

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.

cs.CL↗

arXiv2025

Augmenting Coaching with GenAI: Insights into Use, Effectiveness, and Future Potential

The integration of generative AI (GenAI) tools, particularly large language models (LLMs), is transforming professional coaching workflows. This study explores how coaches use GenAI, the perceived benefits and limitations of these tools, and broader attitudes toward AI-assisted coaching. A survey of 205 coaching professionals reveals widespread adoption of GenAI for research, content creation, and administrative support, while its role in relational and interpretative coaching remains limited. Findings indicate that AI literacy and perceived AI impact strongly predict GenAI adoption, with positive attitudes fostering greater use. Ethical considerations, particularly transparency and data privacy, are a key concern, with frequent AI users demonstrating greater ethical awareness. Regression analyses show that while perceived effectiveness drives GenAI adoption, concerns about AI replacing human coaches do not significantly influence usage. Coaches express interest in future AI capabilities that enhance personalization, real-time feedback, and administrative automation while maintaining human oversight. The study highlights that GenAI functions best as an augmentation tool rather than a replacement, emphasizing the need for AI literacy training, ethical guidelines, and human-centered AI integration. These findings contribute to the ongoing discourse on human-AI collaboration, advocating for responsible and effective AI adoption in professional coaching.

cs.HC↗

arXiv2024

Human-AI Co-Creativity: Exploring Synergies Across Levels of Creative Collaboration

Human-AI co-creativity represents a transformative shift in how humans and generative AI tools collaborate in creative processes. This chapter explores the synergies between human ingenuity and AI capabilities across four levels of interaction: Digital Pen, AI Task Specialist, AI Assistant, and AI Co-Creator. While earlier digital tools primarily facilitated creativity, generative AI systems now contribute actively, demonstrating autonomous creativity in producing novel and valuable outcomes. Empirical evidence from mathematics showcases how AI can extend human creative potential, from computational problem-solving to co-creative partnerships yielding breakthroughs in longstanding challenges. By analyzing these collaborations, the chapter highlights AI's potential to enhance human creativity without replacing it, underscoring the importance of balancing AI's contributions with human oversight and contextual understanding. This integration pushes the boundaries of creative achievements, emphasizing the need for human-centered AI systems that foster collaboration while preserving the unique qualities of human creativity.

cs.HC↗

arXiv2023

Artificial muses: Generative Artificial Intelligence Chatbots Have Risen to Human-Level Creativity

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.

cs.AI↗