Cansu Koyuturk

Emily Theophilou, Cansu Koyuturk, Mona Yavari et al.

Artificial intelligence's (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. However, the ensuing excitement has led to negative sentiments, even as AI methods demonstrate remarkable contributions (e.g. in health and genetics). A key factor contributing to this sentiment is the misleading perception that LLMs can effortlessly provide solutions across domains, ignoring their limitations such as hallucinations and reasoning constraints. Acknowledging AI fallibility is crucial to address the impact of dogmatic overconfidence in possibly erroneous suggestions generated by LLMs. At the same time, it can reduce fear and other negative attitudes toward AI. This necessitates comprehensive AI literacy interventions that educate the public about LLM constraints and effective usage techniques, i.e prompting strategies. With this aim, a pilot educational intervention was performed in a high school with 21 students. It involved presenting high-level concepts about intelligence, AI, and LLMs, followed by practical exercises involving ChatGPT in creating natural educational conversations and applying established prompting strategies. Encouraging preliminary results emerged, including high appreciation of the activity, improved interaction quality with the LLM, reduced negative AI sentiments, and a better grasp of limitations, specifically unreliability, limited understanding of commands leading to unsatisfactory responses, and limited presentation flexibility. Our aim is to explore AI acceptance factors and refine this approach for more controlled future studies.

Cansu Koyuturk, Mona Yavari, Emily Theophilou et al.

Educational chatbots come with a promise of interactive and personalized learning experiences, yet their development has been limited by the restricted free interaction capabilities of available platforms and the difficulty of encoding knowledge in a suitable format. Recent advances in language learning models with zero-shot learning capabilities, such as ChatGPT, suggest a new possibility for developing educational chatbots using a prompt-based approach. We present a case study with a simple system that enables mixed-turn chatbot interactions and discuss the insights and preliminary guidelines obtained from initial tests. We examine ChatGPT's ability to pursue multiple interconnected learning objectives, adapt the educational activity to users' characteristics, such as culture, age, and level of education, and its ability to use diverse educational strategies and conversational styles. Although the results are encouraging, challenges are posed by the limited history maintained for the conversation and the highly structured form of responses by ChatGPT, as well as their variability, which can lead to an unexpected switch of the chatbot's role from a teacher to a therapist. We provide some initial guidelines to address these issues and to facilitate the development of effective educational chatbots.

Cansu Koyuturk, Sabrina Guidotti, Dimitri Ognibene

Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration. However, their tendency toward sycophancy, aligning with user beliefs even when incorrect, raises concerns for learning and decision-making, especially for less knowledgeable users. This study investigates how sycophantic alignment emerges in authentic multi-turn human-AI interactions and whether interventions targeting increasing AI literacy and prompting competencies can mitigate its effects. In a controlled mixed-design experiment, 60 participants completed analytical survival ranking tasks by first generating individual rankings and then making final decisions after collaborating with an AI assistant, both before and after receiving either general or sycophancy-focused prompting training. Preliminary results show that LLMs are highly sensitive to user input: lower-quality initial responses lead to poorer AI advice, suggesting that the model mirrors or incorporates user reasoning rather than correcting it or offering better alternatives that are missing or less frequent in the conversation. Critically, the propagation of user errors into AI responses significantly reduced both the quality of AI feedback and final user task performance, revealing a form of contextual sycophantic dependence. While the intervention did not eliminate the propagation of contextual errors, it significantly improved AI advice by reducing the direct mirroring of incorrect user rankings. These findings suggest that prompting and AI literacy alone may be insufficient to ensure epistemically independent AI support, highlighting the need for system-level approaches that better promote critical engagement in human-AI collaboration.

Chiara Antico, Stefano Giordano, Cansu Koyuturk et al.

Natural language processing skills of Large Language Models (LLMs) are unprecedented, having wide diffusion and application in different tasks. This pilot study focuses on specializing ChatGPT behavior through a Retrieval-Augmented Generation (RAG) system using the OpenAI custom GPTs feature. The purpose of our chatbot, called Unimib Assistant, is to provide information and solutions to the specific needs of University of Milano-Bicocca (Unimib) students through a question-answering approach. We provided the system with a prompt highlighting its specific purpose and behavior, as well as university-related documents and links obtained from an initial need-finding phase, interviewing six students. After a preliminary customization phase, a qualitative usability test was conducted with six other students to identify the strengths and weaknesses of the chatbot, with the goal of improving it in a subsequent redesign phase. While the chatbot was appreciated for its user-friendly experience, perceived general reliability, well-structured responses, and conversational tone, several significant technical and functional limitations emerged. In particular, the satisfaction and overall experience of the users was impaired by the system's inability to always provide fully accurate information. Moreover, it would often neglect to report relevant information even if present in the materials uploaded and prompt given. Furthermore, it sometimes generated unclickable links, undermining its trustworthiness, since providing the source of information was an important aspect for our users. Further in-depth studies and feedback from other users as well as implementation iterations are planned to refine our Unimib Assistant.

Cansu Koyuturk, Emily Theophilou, Sabrina Patania et al.

Large Language Models (LLMs) have transformed human-computer interaction by enabling natural language-based communication with AI-powered chatbots. These models are designed to be intuitive and user-friendly, allowing users to articulate requests with minimal effort. However, despite their accessibility, studies reveal that users often struggle with effective prompting, resulting in inefficient responses. Existing research has highlighted both the limitations of LLMs in interpreting vague or poorly structured prompts and the difficulties users face in crafting precise queries. This study investigates learner-AI interactions through an educational experiment in which participants receive structured guidance on effective prompting. We introduce and compare three types of prompting guidelines: a task-specific framework developed through a structured methodology and two baseline approaches. To assess user behavior and prompting efficacy, we analyze a dataset of 642 interactions from 107 users. Using Von NeuMidas, an extended pragmatic annotation schema for LLM interaction analysis, we categorize common prompting errors and identify recurring behavioral patterns. We then evaluate the impact of different guidelines by examining changes in user behavior, adherence to prompting strategies, and the overall quality of AI-generated responses. Our findings provide a deeper understanding of how users engage with LLMs and the role of structured prompting guidance in enhancing AI-assisted communication. By comparing different instructional frameworks, we offer insights into more effective approaches for improving user competency in AI interactions, with implications for AI literacy, chatbot usability, and the design of more responsive AI systems.

Arian Fooroogh Mand Arabi, Cansu Koyuturk, Michael O'Mahony et al.

This paper presents the iterative development of Habit Coach, a GPT-based chatbot designed to support users in habit change through personalized interaction. Employing a user-centered design approach, we developed the chatbot using a Retrieval-Augmented Generation (RAG) system, which enables behavior personalization without retraining the underlying language model (GPT-4). The system leverages document retrieval and specialized prompts to tailor interactions, drawing from Cognitive Behavioral Therapy (CBT) and narrative therapy techniques. A key challenge in the development process was the difficulty of translating declarative knowledge into effective interaction behaviors. In the initial phase, the chatbot was provided with declarative knowledge about CBT via reference textbooks and high-level conversational goals. However, this approach resulted in imprecise and inefficient behavior, as the GPT model struggled to convert static information into dynamic and contextually appropriate interactions. This highlighted the limitations of relying solely on declarative knowledge to guide chatbot behavior, particularly in nuanced, therapeutic conversations. Over four iterations, we addressed this issue by gradually transitioning towards procedural knowledge, refining the chatbot's interaction strategies, and improving its overall effectiveness. In the final evaluation, 5 participants engaged with the chatbot over five consecutive days, receiving individualized CBT interventions. The Self-Report Habit Index (SRHI) was used to measure habit strength before and after the intervention, revealing a reduction in habit strength post-intervention. These results underscore the importance of procedural knowledge in driving effective, personalized behavior change support in RAG-based systems.

Dimitri Ognibene, Gregor Donabauer, Emily Theophilou et al.

The use of large language model (LLM)-powered chatbots, such as ChatGPT, has become popular across various domains, supporting a range of tasks and processes. However, due to the intrinsic complexity of LLMs, effective prompting is more challenging than it may seem. This highlights the need for innovative educational and support strategies that are both widely accessible and seamlessly integrated into task workflows. Yet, LLM prompting is highly task- and domain-dependent, limiting the effectiveness of generic approaches. In this study, we explore whether LLM-based methods can facilitate learning assessments by using ad-hoc guidelines and a minimal number of annotated prompt samples. Our framework transforms these guidelines into features that can be identified within learners' prompts. Using these feature descriptions and annotated examples, we create few-shot learning detectors. We then evaluate different configurations of these detectors, testing three state-of-the-art LLMs and ensembles. We run experiments with cross-validation on a sample of original prompts, as well as tests on prompts collected from task-naive learners. Our results show how LLMs perform on feature detection. Notably, GPT- 4 demonstrates strong performance on most features, while closely related models, such as GPT-3 and GPT-3.5 Turbo (Instruct), show inconsistent behaviors in feature classification. These differences highlight the need for further research into how design choices impact feature selection and prompt detection. Our findings contribute to the fields of generative AI literacy and computer-supported learning assessment, offering valuable insights for both researchers and practitioners.

Sabrina Patania, Luca Annese, Cansu Koyuturk et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in processing extensive offline datasets. However, they often face challenges in acquiring and integrating complex, knowledge online. Traditional AI training paradigms, predominantly based on supervised learning or reinforcement learning, mirror a 'Piagetian' model of independent exploration. These approaches typically rely on large datasets and sparse feedback signals, limiting the models' ability to learn efficiently from interactions. Drawing inspiration from Vygotsky's sociocultural theory, this study explores the potential of socially mediated learning paradigms to address these limitations. We introduce a dynamic environment, termed the 'AI Social Gym', where an AI learner agent engages in dyadic pedagogical dialogues with knowledgeable AI teacher agents. These interactions emphasize external, structured dialogue as a core mechanism for knowledge acquisition, contrasting with methods that depend solely on internal inference or pattern recognition. Our investigation focuses on how different pedagogical strategies impact the AI learning process in the context of ontology acquisition. Empirical results indicate that such dialogic approaches-particularly those involving mixed-direction interactions combining top-down explanations with learner-initiated questioning-significantly enhance the LLM's ability to acquire and apply new knowledge, outperforming both unidirectional instructional methods and direct access to structured knowledge, formats typically present in training datasets. These findings suggest that integrating pedagogical and psychological insights into AI and robot training can substantially improve post-training knowledge acquisition and response quality. This approach offers a complementary pathway to existing strategies like prompt engineering