arXiv subjects

Tanja Käser

Publications and source records attributed to Tanja Käser.

At least 19 recordsLinked to original sources

arXiv2026

Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes

Writing high-quality procedural texts is a challenging task for many learners. While example-based learning has shown promise as a feedback approach, a limitation arises when all learners receive the same content without considering their individual input or prior knowledge. Consequently, some learners struggle to grasp or relate to the feedback, finding it redundant and unhelpful. To address this issue, we present RELEX, an adaptive learning system designed to enhance procedural writing through personalized example-based learning. The core of our system is a multi-step example retrieval pipeline that selects a higher quality and contextually relevant example for each learner based on their unique input. We instantiate our system in the domain of cooking recipes. Specifically, we leverage a fine-tuned Large Language Model to predict the quality score of the learner's cooking recipe. Using this score, we retrieve recipes with higher quality from a vast database of over 180,000 recipes. Next, we apply BM25 to select the semantically most similar recipe in real-time. Finally, we use domain knowledge and regular expressions to enrich the selected example recipe with personalized instructional explanations. We evaluate RELEX in a 2 x 2 controlled study (personalized vs. non-personalized examples, reflective prompts vs. none) with 200 participants. Our results show that providing tailored examples contributes to better writing performance and user experience.

cs.HC↗

arXiv2026

"Piecing Data Connections Together Like a Puzzle": Effects of Increasing Task Complexity on the Effectiveness of Data Storytelling Enhanced Visualisations

The emerging concept of data storytelling (DS) suggests that enhancing visualisations with annotations and narratives can make complex data more insightful than conventional visualisations. Previous works found that DS-enhanced visualisations are more effective than conventional visualisations for simple tasks like identifying key data points or the main message. However, no previous work has explored the extent to which DS enhancements influence task completion across different levels of cognitive complexity. We address this gap by presenting the results of a study where 128 participants completed tasks based on four visualisations (two line charts and two choropleth maps, either with or without DS elements) spanning a range of complexity based on Bloom's taxonomy, which has been applied in data visualisation to categorise tasks hierarchically from lower to higher-order thinking. Results suggest that while DS-enhanced visualisations effectively support lower-order tasks (finding data points and understanding insights), they don't necessarily aid the correct completion of higher-order tasks (application, analysis, evaluation and creation). However, DS enhancements improve how efficiently participants complete complex tasks.

cs.HC↗

arXiv2026

EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics

Large language models (LLMs) are increasingly deployed as tutors, but it is unclear whether they support all students equally well. We introduce \textbf{EduFair-Bench}, a benchmark for auditing the pedagogical fairness of LLM tutors---whether tutoring quality varies systematically with student demographics. EduFair-Bench pairs a multi-domain question bank (mathematics, physics, chemistry) with a controlled simulation in which a fixed LLM student interacts with each tutor across nine demographic levels spanning four dimensions: gender, immigration background, first language, and socioeconomic status (SES). Tutoring quality is scored on five turn-level pedagogical metrics and four conversation-level dimensions, using an LLM judge validated against three-annotator consensus on 180 tutor turns. Bias is measured via paired Wilcoxon signed-rank tests and bootstrap effect-size confidence intervals. Two ablations (demographic cues conveyed through names; conflicting demographic information between tutor and student) disentangle tutor-driven from student-driven bias. Across five tutors, we find that model capability and demographic fairness are largely orthogonal: the smallest model is the most consistent while the four more capable tutors all exhibit wide demographic gaps with no clear capability-to-fairness ordering, pedagogy-specific RL training redistributes rather than removes bias, and language- and immigration-related cues produce larger gaps than gender- and SES-related cues.

cs.AI↗

arXiv2026

From Substitution to Scaffolding: Breaking the Self-Reinforcing Harm Cycle of AI in Education (and Beyond)

Artificial intelligence is being adopted in educational settings faster than its consequences are understood. We argue that the central risk is misalignment: AI that eliminates human effort erodes the very capacities education is meant to build. We organize this risk into an integrative framework of four interrelated dimensions -cognition, agency, emotional well-being, and ethics- linked by a self-reinforcing cycle where cognitive offloading reduces effort, weakens agency, and compounds emotional and ethical harm. We ground the framework in the perspective of a small cohort of students: an exploratory analysis of 49 International Baccalaureate argumentative essays about the impact of AI reveals that learners perceive these risks, with $80\%$ of essays reporting that AI reliance reduces thinking. At the same time, the essays articulate a consistent vision of the AI the students want: systems that support rather than replace learning by withholding immediate answers, prompting recall, and encouraging reflection through questions instead of solutions. These desiderata closely align with established principles from the learning sciences. Building on these insights, we propose a single design principle, scaffold, do not substitute. We argue that this principle extends beyond education. It represents a broader challenge for the AI ecosystem: any system that mediates human thinking can either weaken human capabilities through substitution or strengthen them through scaffolding. We conclude by outlining a research agenda for developing AI systems that foster enduring human capacity, an imperative not only for learners but, ultimately, for democratic societies.

cs.HC↗

arXiv2026

PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering

LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers. Tutors must choose when to scaffold reasoning, hint, give feedback, explain, or invite reflection. Existing prompting and training methods improve pedagogical alignment, but lack reliable inference-time control over pedagogical strategies. We introduce PIVOT, an activation-steering framework that learns preference-based intervention vectors online for frozen LLM tutors. PIVOT uses a seven-category tutor-move taxonomy and a generate-label-optimise loop, where a human-validated LLM judge identifies target and confusable non-target moves to construct preference pairs for multi-layer residual-stream steering. Across held-out and out-of-domain tutoring data, PIVOT controls tutor moves while preserving relevance and fluency, and its directions can be scaled, transferred, and composed at inference time. In a user study with 30 teachers, 73.3% of participants preferred steered conversations over neutral baseline interactions using the same prompt, and rated the controls as clear, usable, and pedagogically meaningful.

cs.HC↗

arXiv2026

Tracing Persona Vectors Through LLM Pretraining

How large language models internally represent high-level behaviors is a core interpretability question with direct relevance to AI safety: it determines what we can detect, audit, or intervene on. Recent work has shown that traits such as evil or sycophancy correspond to linear directions in the internal activations, the so-called persona vectors. Although these vectors are now routinely utilized to inspect and steer model behavior in safety-relevant settings, how these representations are formed during training remains unknown. To address this gap, we trace persona vectors across the pretraining of OLMo-3-7B, finding that persona vectors form remarkably early -- within 0.22% of OLMo-3 pretraining -- and remain effective for steering the fully post-trained instruct models. Although core representations are formed early on, persona vectors continue to refine geometrically and semantically throughout pretraining. We further compare alternative elicitation strategies and find that all yield effective directions, with each strategy surfacing qualitatively distinct facets of the underlying persona. Replicating our analysis on Apertus-8B reveals that our findings transfer qualitatively beyond OLMo-3. Our results establish persona representations as stable features of early pretraining and open a path to studying how training forms, refines, and shapes them.

cs.CL↗

arXiv2026

Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks

Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work evaluates pedagogical quality via answer leakage-the disclosure of complete solutions instead of scaffolding-but typically assumes well-intentioned learners, leaving tutor robustness under student misuse largely unexplored. In this paper, we study scenarios where students behave adversarially and aim to obtain the correct answer from the tutor. We evaluate a broad set of LLM-based tutor models, including different model families, pedagogically aligned models, and a multi-agent design, under a range of adversarial student attacks. We adapt six groups of adversarial and persuasive techniques to the educational setting and use them to probe how likely a tutor is to reveal the final answer. We evaluate answer leakage robustness using different types of in-context adversarial student agents, finding that they often fail to carry out effective attacks. We therefore introduce an adversarial student agent that we fine-tune to jailbreak LLM-based tutors, which we propose as the core of a standardized benchmark for evaluating tutor robustness. Finally, we present simple but effective defense strategies that reduce answer leakage and strengthen the robustness of LLM-based tutors in adversarial scenarios.

cs.CR↗

arXiv2026

Structuring versus Problematizing: How LLM-based Agents Scaffold Learning in Diagnostic Reasoning

Supporting students in developing diagnostic reasoning is a key challenge across educational domains. Novices often face cognitive biases such as premature closure and over-reliance on heuristics, and they struggle to transfer diagnostic strategies to new cases. Scenario-based learning (SBL) enhanced by Learning Analytics (LA) and large language models (LLM) offers a promising approach by combining realistic case experiences with personalized scaffolding. Yet, how different scaffolding approaches shape reasoning processes remains insufficiently explored. This study introduces PharmaSim Switch, an SBL environment for pharmacy technician training, extended with an LA- and LLM-powered pharmacist agent that implements pedagogical conversations rooted in two theory-driven scaffolding approaches: \emph{structuring} and \emph{problematizing}, as well as a student learning trajectory. In a between-groups experiment, 63 vocational students completed a learning scenario, a near-transfer scenario, and a far-transfer scenario under one of the two scaffolding conditions. Results indicate that both scaffolding approaches were effective in supporting the use of diagnostic strategies. Performance outcomes were primarily influenced by scenario complexity rather than students' prior knowledge or the scaffolding approach used. The structuring approach was associated with more accurate Active and Interactive participation, whereas problematizing elicited more Constructive engagement. These findings underscore the value of combining scaffolding approaches when designing LA- and LLM-based systems to effectively foster diagnostic reasoning.

cs.HC↗

arXiv2026

Scalable and Explainable Learner-Video Interaction Prediction using Multimodal Large Language Models

Learners' use of video controls in educational videos provides implicit signals of cognitive processing and instructional design quality, yet the lack of scalable and explainable predictive models limits instructors' ability to anticipate such behavior before deployment. We propose a scalable, interpretable pipeline for predicting population-level watching, pausing, skipping, and rewinding behavior as proxies for cognitive load from video content alone. Our approach leverages multimodal large language models (MLLMs) to compute embeddings of short video segments and trains a neural classifier to identify temporally fine-grained interaction peaks. Drawing from multimedia learning theory on instructional design for optimal cognitive load, we code features of the video segments using GPT-5 and employ them as a basis for interpreting model predictions via concept activation vectors. We evaluate our pipeline on 77 million video control events from 66 online courses. Our findings demonstrate that classifiers based on MLLM embeddings reliably predict interaction peaks, generalize to unseen academic fields, and encode interpretable, theory-relevant instructional concepts. Overall, our results show the feasibility of cost-efficient, interpretable pre-screening of educational video design and open new opportunities to empirically examine multimedia learning theory at scale.

cs.AI↗

arXiv2026

REFINE: Real-world Exploration of Interactive Feedback and Student Behaviour

Formative feedback is central to effective learning, yet providing timely, individualised feedback at scale remains a persistent challenge. While recent work has explored the use of large language models (LLMs) to automate feedback, most existing systems still conceptualise feedback as a static, one-way artifact, offering limited support for interpretation, clarification, or follow-up. In this work, we introduce REFINE, a locally deployable, multi-agent feedback system built on small, open-source LLMs that treats feedback as an interactive process. REFINE combines a pedagogically-grounded feedback generation agent with an LLM-as-a-judge-guided regeneration loop using a human-aligned judge, and a self-reflective tool-calling interactive agent that supports student follow-up questions with context-aware, actionable responses. We evaluate REFINE through controlled experiments and an authentic classroom deployment in an undergraduate computer science course. Automatic evaluations show that judge-guided regeneration significantly improves feedback quality, and that the interactive agent produces efficient, high-quality responses comparable to a state-of-the-art closed-source model. Analysis of real student interactions further reveals distinct engagement patterns and indicates that system-generated feedback systematically steers subsequent student inquiry. Our findings demonstrate the feasibility and effectiveness of multi-agent, tool-augmented feedback systems for scalable, interactive feedback.

cs.AI↗

arXiv2026

Moving Beyond Review: Applying Language Models to Planning and Translation in Reflection

Reflective writing is known to support the development of students' metacognitive skills, yet learners often struggle to engage in deep reflection, limiting learning gains. Although large language models (LLMs) have been shown to improve writing skills, their use as conversational agents for reflective writing has produced mixed results and has largely focused on providing feedback on reflective texts, rather than support during planning and organizing. In this paper, inspired by the Cognitive Process Theory of writing (CPT), we propose the first application of LLMs to the planning and translation steps of reflective writing. We introduce Pensée, a tool to explore the effects of explicit AI support during these stages by scaffolding structured reflection planning using a conversational agent, and supporting translation by automatically extracting key concepts. We evaluate Pensée in a controlled between-subjects experiment (N=93), manipulating AI support across writing phases. Results show significantly greater reflection depth and structural quality when learners receive support during planning and translation stages of CPT, though these effects reduce in a delayed post-test. Analyses of learner behavior and perceptions further illustrate how CPT-aligned conversational support shapes reflection processes and learner experience, contributing empirical evidence for theory-driven uses of LLMs in AI-supported reflective writing.

cs.HC↗

arXiv2026

AI in Education Beyond Learning Outcomes: Cognition, Agency, Emotion, and Ethics

Artificial intelligence (AI) is rapidly being integrated into educational contexts, promising personalized support and increased efficiency. However, growing evidence suggests that the uncritical adoption of AI may produce unintended harms that extend beyond individual learning outcomes to affect broader societal goals. This paper examines the societal implications of AI in education through an integrative framework with four interrelated dimensions: cognition, agency, emotional well-being, and ethics. Drawing on research from education, cognitive science, psychology, and ethics, we synthesize existing evidence to show how AI-driven cognitive offloading, diminished learner agency, emotional disengagement, and surveillance-oriented practices can mutually reinforce one another. We argue that these dynamics risk undermining critical thinking, intellectual autonomy, emotional resilience, and trust, capacities that are foundational both for effective learning and also for democratic participation and informed civic engagement. Moreover, AI's impact is contingent on design and governance: pedagogically aligned, ethically grounded, and human-centered AI systems can scaffold effortful reasoning, support learner agency, and preserve meaningful social interaction. By integrating fragmented strands of prior research into a unified framework, this paper advances the discourse on responsible AI in education and offers actionable implications for educators, designers, and institutions. Ultimately, the paper contends that the central challenge is not whether AI should be used in education, but how it can be designed and governed to support learning while safeguarding the social and civic purposes of education.

cs.HC↗

arXiv2026

Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays

Automated Essay Scoring systems have traditionally focused on holistic scores, limiting their pedagogical usefulness, especially in the case of complex essay genres such as argumentative writing. In educational contexts, teachers and learners require interpretable, trait-level feedback that aligns with instructional goals and established rubrics. In this paper, we study trait-based Automatic Argumentative Essay Scoring using two complementary modeling paradigms designed for realistic educational deployment: (1) structured in-context learning with small open-source LLMs, and (2) a supervised, encoder-based BigBird model with a CORAL-style ordinal regression formulation, optimized for long-sequence understanding. We conduct a systematic evaluation on the ASAP++ dataset, which includes essay scores across five quality traits, offering strong coverage of core argumentation dimensions. LLMs are prompted with designed, rubric-aligned in-context examples, along with feedback and confidence requests, while we explicitly model ordinality in scores with the BigBird model via the rank-consistent CORAL framework. Our results show that explicitly modeling score ordinality substantially improves agreement with human raters across all traits, outperforming LLMs and nominal classification and regression-based baselines. This finding reinforces the importance of aligning model objectives with rubric semantics for educational assessment. At the same time, small open-source LLMs achieve a competitive performance without task-specific fine-tuning, particularly for reasoning-oriented traits, while enabling transparent, privacy-preserving, and locally deployable assessment scenarios. Our findings provide methodological, modeling, and practical insights for the design of AI-based educational systems that aim to deliver interpretable, rubric-aligned feedback for argumentative writing.

cs.CL↗

arXiv2025

Leveraging Small LLMs for Argument Mining in Education: Argument Component Identification, Classification, and Assessment

Argument mining algorithms analyze the argumentative structure of essays, making them a valuable tool for enhancing education by providing targeted feedback on the students' argumentation skills. While current methods often use encoder or encoder-decoder deep learning architectures, decoder-only models remain largely unexplored, offering a promising research direction. This paper proposes leveraging open-source, small Large Language Models (LLMs) for argument mining through few-shot prompting and fine-tuning. These models' small size and open-source nature ensure accessibility, privacy, and computational efficiency, enabling schools and educators to adopt and deploy them locally. Specifically, we perform three tasks: segmentation of student essays into arguments, classification of the arguments by type, and assessment of their quality. We empirically evaluate the models on the Feedback Prize - Predicting Effective Arguments dataset of grade 6-12 students essays and demonstrate how fine-tuned small LLMs outperform baseline methods in segmenting the essays and determining the argument types while few-shot prompting yields comparable performance to that of the baselines in assessing quality. This work highlights the educational potential of small, open-source LLMs to provide real-time, personalized feedback, enhancing independent learning and writing skills while ensuring low computational cost and privacy.

cs.CL↗

arXiv2025

SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling

Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for pedagogically valid responses. These constraints require small, open-source models that can run locally and reliably ground their outputs in correct information. We introduce SCRIBE, a framework for multi-hop, tool-augmented reasoning designed to generate valid responses to student questions about feedback reports. SCRIBE combines domain-specific tools with a self-reflective inference pipeline that supports iterative reasoning, tool use, and error recovery. We distil these capabilities into 3B and 8B models via two-stage LoRA fine-tuning on synthetic GPT-4o-generated data. Evaluation with a human-aligned GPT-Judge and a user study with 108 students shows that 8B-SCRIBE models achieve comparable or superior quality to much larger models in key dimensions such as relevance and actionability, while being perceived on par with GPT-4o and Llama-3.3 70B by students. These findings demonstrate the viability of SCRIBE for low-resource, privacy-sensitive educational applications.

cs.CL↗

arXiv2025

Do AI tutors empower or enslave learners? Toward a critical use of AI in education

The increasing integration of AI tools in education presents both opportunities and challenges, particularly regarding the development of the students' critical thinking skills. This position paper argues that while AI can support learning, its unchecked use may lead to cognitive atrophy, loss of agency, emotional risks, and ethical concerns, ultimately undermining the core goals of education. Drawing on cognitive science and pedagogy, the paper explores how over-reliance on AI can disrupt meaningful learning, foster dependency and conformity, undermine the students' self-efficacy, academic integrity, and well-being, and raise concerns about questionable privacy practices. It also highlights the importance of considering the students' perspectives and proposes actionable strategies to ensure that AI serves as a meaningful support rather than a cognitive shortcut. The paper advocates for an intentional, transparent, and critically informed use of AI that empowers rather than diminishes the learner.

cs.CY↗

arXiv2025

ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection

The widespread adoption of chat interfaces based on Large Language Models (LLMs) raises concerns about promoting superficial learning and undermining the development of critical thinking skills. Instead of relying on LLMs purely for retrieving factual information, this work explores their potential to foster deeper reasoning by generating critical questions that challenge unsupported or vague claims in debate interventions. This study is part of a shared task of the 12th Workshop on Argument Mining, co-located with ACL 2025, focused on automatic critical question generation. We propose a two-step framework involving two small-scale open source language models: a Questioner that generates multiple candidate questions and a Judge that selects the most relevant ones. Our system ranked first in the shared task competition, demonstrating the potential of the proposed LLM-based approach to encourage critical engagement with argumentative texts.

cs.CL↗

arXiv2025

Educators' Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting

The rapid development of Large Language Models (LLMs) opens up the possibility of using them as personal tutors. This has led to the development of several intelligent tutoring systems and learning assistants that use LLMs as back-ends with various degrees of engineering. In this study, we seek to compare human tutors with LLM tutors in terms of engagement, empathy, scaffolding, and conciseness. We ask human tutors to annotate and compare the performance of an LLM tutor with that of a human tutor in teaching grade-school math word problems on these qualities. We find that annotators with teaching experience perceive LLMs as showing higher performance than human tutors in all 4 metrics. The biggest advantage is in empathy, where 80% of our annotators prefer the LLM tutor more often than the human tutors. Our study paints a positive picture of LLMs as tutors and indicates that these models can be used to reduce the load on human teachers in the future.

cs.ET↗