Educational Dialogue Systems

Teachers increasingly configure educational chatbots through natural-language instructions, but how these bots fail in real-world use remains poorly understood. We introduce EduWild, a dataset of 1,726 conversations with 217 teacher-configured chatbots, each paired with the instructions and configuration behind it, including 900 conversations from the intended end users of 35 deployed chatbots. We develop a 29-code taxonomy covering factual, workflow, diagnostic, and pedagogical failures and apply it using a human-calibrated LLM judge. The most frequent failures are lapses in following teacher intent --- bots skip required workflow steps (53.8% of end-user conversations), omit expectation setup (33.4%), and overload learners with information or questions (37.1%). Guided by these findings, we design a prompt-based harness targeting the six most frequent failure modes. In a study with 200 college students across ten bots, the harness reduces the mean number of target failure codes per conversation from 1.406 to 0.489, a 65.2% relative reduction with bots weighted equally. These findings show how real-world failure analysis can guide practical improvements to educational chatbots.

Does unrestricted AI access bypass the cognitive effort required for learning, or does it streamline knowledge acquisition? This paper reports on a study where we compare three designs for user-AI interaction in a learning context: (1) an unrestricted conversational bot like ChatGPT, (2) a pedagogically constrained bot that guides through hints without giving final answers, which we refer to as the Socratic mode; and (3) a non-conversational adaptive tutoring system that adjusts difficulty in real-time based on the user's cognitive engagement derived from the brain signals. Fifty study participants were tasked with learning about nuclear safety protocols, a domain chosen for its zero-prior knowledge baseline. The participants progressed through an instructional video, a pre-test, an AI-driven assessment phase, which varied in the three conditions, and an immediate post-test. The nature of the questions centered primarily on factual knowledge acquisition, but it still required participants to have a global understanding of the concepts in order to answer the questions correctly. A Muse headband was used to derive the cognitive engagement of all users in all conditions. The unrestricted chatbot produced higher learning gains (delta) than both constrained modes (p < .03, d > 0.80), while the adaptive condition generated significantly higher EEG engagement (p = .018). The cluster analysis of chatbot usage and discussion patterns by users showed that most participants in the unrestricted-mode adopted a direct answer-retrieval strategy, while participants in the Socratic-mode initially attempted to reason through the hints before progressively disengaging. Consequently, this also suggests that the success of the unrestricted AI is not an evidence of deeper learning, but rather a result of the immediate post-test evaluation after the training phase.

Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains such as education, healthcare, and finance. However, existing benchmarks typically assume perfectly accurate tool outputs, overlooking the reality that deployed systems must operate with noisy tools and human decision-makers whose trust in the agent is itself uncertain. Such conditions are common in practice, for example, a clinician using a diagnostic prediction tool or an advisor relying on a model that forecasts student outcomes from historical records. We introduce PREDACTBENCH, a benchmark for evaluating dialogue agents paired with statistically imperfect tools, using education as a measurable testbed where ground truth outcomes and clear intervention decisions are available. First, we build a benchmark for AI-assisted human decision-making, where the AI uses noisy predictors to help guide a user. Second, we introduce episode-level Relative AI-Reliance (RAIR) and Relative self-reliance (RSR) metrics, extending prior trust calibration framework to multi-turn dialogue. Third, we evaluate 13 state-of-the-art closed and open source LLMs on two educational datasets, OULAD (real assessment trajectories from the UK Open University) and PREDACT-CS (60 courses with real final grade outcomes and synthetically generated weekly score trajectories), alongside a human study with instructors and teaching assistants. We find that when tools are noisy, SOTA models are supposed to provide visibility to teachers so that they do not over-rely on wrong suggestions or hallucinations, but current models fail to do that. We offer PREDACTBENCH to help build better LLMs as AI decision support systems to help teachers.

LLM tutoring poses a measurement problem: can a general-purpose helpfulness rubric distinguish direct answer-giving from pedagogical guidance? We audit this signal in a pre-registered study. Within each of three tutor bases, we compare conversational and pedagogical policies instantiated with the same underlying model and paired with one fixed weak simulated student. Deterministic detectors measure answer leakage and next-turn independent work. Claude Opus 4.8 is the frozen, condition-blind primary judge. After the Opus scores were fixed, GPT-5.6 Sol was prospectively specified for a post hoc robustness audit of the same 1,179 confirmatory answer-phase tutor turns under the frozen helpfulness and pedagogy rubrics. On the primary base under Opus, the policies do not differ significantly in helpfulness but are perfectly rank-separated under the pedagogy rubric (Cliff's $|δ|{=}0.10$ vs. $1.0$). Across the two judges, pedagogy contrasts retain their direction where detected, whereas the helpfulness ordering is judge-contingent, reversing between judges on two of three bases. In an Opus-only ablation, seven primary-base policies span $2.3$ points in mean judged pedagogy within a $0.25$-point band of mean judged helpfulness. Separately, answer-revealing turns are followed by less independent student work on every base, a result that is judge-invariant by construction. In this controlled setting, general-purpose helpfulness is not a reliable pedagogy signal. Tutor evaluation should pair pedagogy-targeted rubrics with deterministic process measures.

Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), and directness (R_dir), together with a K_query correction for student-introduced terms. We introduce Scaffolding Effectiveness (SE) and Conversation Depth (CD) to evaluate outcomes beyond surface fluency. On 30 held-out questions, the best GRPO variant improves SE from 30.0% to 63.3% and lowers keyword leakage from 30.0% to 13.3%. Notably, this best variant omits the directness penalty during optimization, suggesting that explicit anti-leakage terms can conflict with gradient-based behavioral alignment. An unaligned Qwen-72B baseline reaches 0% SE and 96.7% leakage, showing that scale alone does not induce Socratic behavior.

In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objective log data from 77,543 students enrolled in distance studies, we examine usage patterns across gender, age group, study cluster, degree, and study mode. To date, existing research on educational chatbots has largely relied on comparatively small samples and self-reported survey data, while large-scale evidence on actual usage behavior remains limited. Our findings show that Syntea is already embedded in the study routines of many learners, but that usage differs across demographic and structural contexts. By identifying these patterns, our study provides an empirical basis for the further development of AI-based learning support and contributes a large-scale analysis of educational chatbot usage in higher education.

LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines. We develop and test a system with subject-aware prompting, based on 14 pedagogical features (e.g., tutor scaffolding, student understanding) extracted from raw transcripts. We first train a prompt routing model in a simulation environment, and then deploy it for online adaptation with actual high-school students. The simulation benchmark shows the router outperforming two static baselines ($0.694$ vs. $0.647$ and $0.64$, $p<0.001$). A/B testing ($N=656$ conversations from 359 students) shows sim-to-real transfer where the model switches from analytical to scaffolding learning strategies. Our adaptive prompt selection mechanism improves instructional efficiency, maintains pedagogical quality and reduces interactions by around 3 turns ($p=0.007$). While a greedy router achieves a comparable exercise conversion rate with the baseline ($19.1\%$ vs. $19.6\%$), a stochastic router that samples strategies leads to a higher conversion rate ($28.1\%$).

Large language models are now widely used for everyday learning, but the underlying interactions are typically unstructured chats rather than following a curriculum. Unlike formal online learning systems, these interactions carry no prior record of the student, so any estimate of what the student already knows must be inferred from the dialogue itself. We show that this gap is not closed by scaling models alone. Frontier and education-tuned LLMs perform poorly when asked to tutor a student over an extended session, because doing so requires three things at once. The tutor must sequence a curriculum, conduct Socratic dialogue, and infer the student's knowledge state from that dialogue. We propose separating these responsibilities. Given a student query, our system constructs a prerequisite knowledge graph in which subtopics are nodes and dependencies are edges, and frames tutoring as deciding which node to teach next and how many dialogue turns to spend on it before moving on. A lightweight PPO policy handles this sequencing decision, while an LLM conducts the Socratic exchange at the chosen node and returns a signal of student progress. Across held-out STEM and non-STEM topics, our PPO-paired tutor outperforms heuristic baselines, frontier general-purpose models, and a model specialised for Socratic dialogue: on both the rate at which students reach full curriculum mastery and the number of turns required. Explicit curriculum structure delivers gains that scaling the underlying model does not.

We present RPO-PDT: a retrieval-grounded, role-play-based dialogue system for adaptive student support in higher education. RPO-PDT is: (1) able to provide institution-specific Personal Development Tutor (PDT) guidance using structured knowledge sources; (2) constrained by explicit persona, boundary, confidentiality, and safety policies; and (3) designed around a reverse-roleplay loop where unresolved interactions are replayed from the student perspective, enabling alternative tutor strategies to be generated and stored as reusable strategy memory. RPO-PDT supports both text-based and Furhat-based embodied interaction for demonstrating grounded, safe, and adaptive student-support dialogue.

Evaluating AI tutor responses requires more than factual correctness: tutors must identify mistakes, locate errors, provide guidance, and offer actionable next steps. We present GRADE, a systematic study of open-source models for pedagogical ability assessment in student-tutor dialogues. Building on the BEA 2025 TutorMind setting, we evaluate 120 configurations across five language models, zero-shot inference, LoRA fine-tuning, synthetic augmentation, CoT+Reasoning, and single-task versus multitask formulations. Gemma3-12B performs best for single-task evaluation, while Gemma3-27B in 8-bit precision is more reliable for multitask prediction. We find that augmentation helps models that struggle with the original data, verification adds limited gains despite higher cost, and CoT+Reasoning is more useful for synthetic data generation than direct classification. We further show that LoRA fine-tuning on structured classification objectives interferes with instruction-following behavior under thinking mode, redirecting generation away from the required evaluation format. Carbon analysis shows that model choice and reasoning mode substantially affect emissions. Overall, GRADE shows that carefully selected open-source LoRA pipelines can match or surpass proprietary and ensemble-based systems on key pedagogical dimensions, with code and data available at https://github.com/pvbgeek/GRADE.

Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora. We present a systematic methodology for transforming structured linguistic resources into specialized AI systems, demonstrating that expert-curated lexical databases can serve as effective foundations for conversational AI development. Our approach converts Hindi WordNet into 1.25 million diverse instruction-response pairs, fine-tunes a 12B-parameter language model using resource-efficient LoRA with 4-bit quantization. Evaluation through a Hindi language learning chatbot demonstrates that structured-knowledge-based systems achieve superior pedagogical effectiveness (91.0 vs. 79.4-83.6 for general-purpose models) while maintaining competitive semantic performance and exceptional consistency. The complete pipeline demonstrates a proof-of-concept methodology using Hindi for developing specialized AI systems for any languages with WordNet resources. This work addresses the critical gap in AI accessibility for low-resource languages, offering a practical alternative to corpus-intensive approaches and potentially enabling specialized AI development for the hundreds of languages with existing WordNet resources.

Chatbots have long been explored as tools to support learning, and recent advances in large language models have significantly expanded the availability of platforms for educators to author AI tutoring chatbots. Yet effective authorship demands more than writing a system prompt; it requires educators to act as learning designers, AI interaction designers, and QA engineers. In practice, however, teachers rarely fulfill these roles. Our formative study found that virtually none systematically tested their bots before deploying them to students. To address this gap, we present PromptDecipher, a system that restructures the authoring workflow around a direct correction-based interaction rather than writing abstract system prompts, teachers interact with a live chat preview and edit undesirable bot responses. An automated pipeline then analyzes the correction, proposes a targeted system prompt rewrite, and validates the change across pre-defined test scenarios. This enforces QA as a first-class activity and scaffolds teachers in roles they would otherwise skip. PromptDecipher will be deployed in an AI for Educators course enrolling hundreds of higher-education instructors. A live prototype (https://teacher-prompting.vercel.app/), an anonymized codebase (https://anonymous.4open.science/r/teacher-prompting-2EDF/), and anonymized demo (https://tinyurl.com/las-prompt-decipher-demo) are available via links in the footnote.

Sub-Saharan Africa faces persistently high student-teacher ratios and shortages of qualified teachers, limiting students' access to personalized learning support and formative assessment. To address this challenge, we present Adesua, a WhatsApp-based AI Teaching Assistant for science education that extends the Kwame for Science platform. Adesua leverages WhatsApp's widespread adoption in Africa to provide accessible, curriculum-aligned learning support for Junior High School (JHS) and Senior High School (SHS) students across West Africa. The system integrates curated textbooks and 33 years of national examination questions with generative AI to enable conversational question answering and automated assessment with feedback via a WhatsApp bot. Students can ask science questions, take timed or untimed multiple-choice tests by topic or exam year, and receive instant grading and detailed explanations of correct and incorrect responses. A 6-month feasibility deployment in 2025 had 56 active users in Ghana, including students and parents. Quantitative evaluation showed a high perceived usefulness, with a helpfulness score of 93.75% for AI-generated answers, albeit with a small number of ratings (n=16). These preliminary results provide a basis for more extensive future evaluation of a WhatsApp-based AI assistant to assess its potential to offer scalable, low-cost personalized learning support and formative assessment in resource-constrained educational contexts.

Computational thinking (CT) is increasingly promoted as a core literacy, yet learners and teachers face challenges in connecting abstract program logic to meaningful outcomes. We design and evaluate RoboBlockly Studio, an integrated interactive system that combines block-based programming, a conversational AI teaching agent, and embodied robot execution. RoboBlockly Studio creates a tight iterative loop of authoring, running, observing, and revising. Informed by interviews with five programming teachers, the system was designed to support four goals: (1) preserving learner agency in computational thinking, (2) making program behavior transparent and interpretable, (3) grounding programming in embodied, classroom-aligned tasks, and (4) scaffolding reflection through pedagogically grounded AI dialogue. We deployed RoboBlockly Studio with 32 high school students, observing how robot and AI feedback influenced students' interactions with code, reflections on problem-solving strategies, and understanding of CT concepts. We discuss design insights and implications for creating interactive, embodied learning environments that integrate AI and robotics to support CT learning in computing education.

Educational NLP systems are typically evaluated using engagement metrics and satisfaction surveys, which are at best a proxy for meeting pedagogical goals. We introduce six computational metrics for automated evaluation of pedagogical alignment in student-AI dialogue. We validate our metrics through analysis of 12,650 messages across 500 conversations from four courses. Using our metrics, we identify a fundamental misalignment: educators design conversational tutors for sustained learning dialogue, but students mainly use them for answer-extraction. Deployment context is the strongest predictor of usage patterns, outweighing student preference or system design: when AI tools are optional, usage concentrates around deadlines; when integrated into course structure, students ask for solutions to verbatim assignment questions. Whole-dialogue evaluation misses these turn-by-turn patterns. Our metrics will enable researchers building educational dialogue systems to measure whether they are achieving their pedagogical goals.

Diagnosing student problem behaviors requires teachers to synthesize multifaceted information, identify behavioral categories, and plan intervention strategies. Although fine-tuned large language models (LLMs) can support this process through multi-turn dialogue, they rarely explain why a strategy is recommended, limiting transparency and teachers' trust. To address this issue, we present an explainable dialogue system built on a fine-tuned LLM. The system uses a hierarchical attribution method based on explainable AI (xAI) to identify dialogue evidence for each recommendation and generate a natural-language explanation based on that evidence. In technical evaluation, the method outperformed baseline approaches in identifying supporting evidence. In a preliminary user study with 22 pre-service teachers, participants who received explanations reported higher trust in the system. These findings suggest a promising direction for improving LLM explainability in educational dialogue systems.

Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapted RAG pipeline for tutoring move annotation. Rather than fine-tuning the generative model, we adapt retrieval by fine-tuning a lightweight embedding model on tutoring corpora and indexing dialogues at the utterance level to retrieve labeled few-shot demonstrations. Evaluated across two real tutoring dialogue datasets (TalkMoves and Eedi) and three LLM backbones (GPT-5.2, Claude Sonnet 4.6, Qwen3-32b), our best configuration achieves Cohen's $κ$ of 0.526-0.580 on TalkMoves and 0.659-0.743 on Eedi, substantially outperforming no-retrieval baselines ($κ= 0.275$-$0.413$ and $0.160$-$0.410$). An ablation study reveals that utterance-level indexing, rather than embedding quality alone, is the primary driver of these gains, with top-1 label match rates improving from 39.7% to 62.0% on TalkMoves and 52.9% to 73.1% on Eedi under domain-adapted retrieval. Retrieval also corrects systematic label biases present in zero-shot prompting and yields the largest improvements for rare and context-dependent labels. These findings suggest that adapting the retrieval component alone is a practical and effective path toward expert-level pedagogical dialogue annotation while keeping the generative model frozen.

Multimodal Large Language Models (MLLMs) offer an opportunity to support multimedia learning through conversational systems grounded in educational content. However, while conversational AI is known to boost engagement, its impact on learning in visually-rich STEM domains remains under-explored. Moreover, there is limited understanding of how multimodality and conversationality jointly influence learning in generative AI systems. This work reports findings from a randomized controlled online study (N = 124) comparing three approaches to learning biology from textbook content: (1) a document-grounded conversational AI with interleaved text-and-image responses (MuDoC), (2) a document-grounded conversational AI with text-only responses (TexDoC), and (3) a textbook interface with semantic search and highlighting (DocSearch). Learners using MuDoC achieved the highest post-test scores and reported the most positive learning experience. Notably, while TexDoC was rated as significantly more engaging and easier to use than DocSearch, it led to the lowest post-test scores, revealing a disconnect between student perceptions and learning outcomes. Interpreted through the lens of the Cognitive Load Theory, these findings suggest that conversationality reduces extraneous load, while visual-verbal integration induced by multimodality increases germane load, leading to better learning outcomes. When conversationality is not complemented by multimodality, reduced cognitive effort may instead inflate perceived understanding without improving learning outcomes.

Higher education instructors often lack timely and pedagogically grounded support, as scalable instructional guidance remains limited and existing tools rely on generic chatbot advice or non-scalable teaching center human-human consultations. We present TeachingCoach, a pedagogically grounded chatbot designed to support instructor professional development through real-time, conversational guidance. TeachingCoach is built on a data-centric pipeline that extracts pedagogical rules from educational resources and uses synthetic dialogue generation to fine-tune a specialized language model that guides instructors through problem identification, diagnosis, and strategy development. Expert evaluations show TeachingCoach produces clearer, more reflective, and more responsive guidance than a GPT-4o mini baseline, while a user study with higher education instructors highlights trade-offs between conversational depth and interaction efficiency. Together, these results demonstrate that pedagogically grounded, synthetic data driven chatbots can improve instructional support and offer a scalable design approach for future instructional chatbot systems.

Dialogue systems have long supported learner reflections, with theoretically grounded, rule-based designs offering structured scaffolding but often struggling to respond to shifts in engagement. Large Language Models (LLMs), in contrast, can generate context-sensitive responses but are not informed by decades of research on how learning interactions should be structured, raising questions about their alignment with pedagogical theories. This paper presents a hybrid dialogue system that embeds LLM responsiveness within a theory-aligned, rule-based framework to support learner reflections in a culturally responsive robotics summer camp. The rule-based structure grounds dialogue in self-regulated learning theory, while the LLM decides when and how to prompt deeper reflections, responding to evolving conversation context. We analyze themes across dialogues to explore how our hybrid system shaped learner reflections. Our findings indicate that LLM-embedded dialogues supported richer learner reflections on goals and activities, but also introduced challenges due to repetitiveness and misalignment in prompts, reducing engagement.

Providing scaffolding through educational chatbots built on Large Language Models (LLM) has potential risks and benefits that remain an open area of research. When students navigate impasses, they ask for help by formulating impasse-driven questions. Within interactions with LLM chatbots, such questions shape the user prompts and drive the pedagogical effectiveness of the chatbot's response. This paper focuses on such student questions from two datasets of distinct learning contexts: formative self-study, and summative assessed coursework. We analysed 6,113 messages from both learning contexts, using 11 different LLMs and three human raters to classify student questions using four existing schemas. On the feasibility of using LLMs as raters, results showed moderate-to-good inter-rater reliability, with higher consistency than human raters. The data showed that 'procedural' questions predominated in both learning contexts, but more so when students prepare for summative assessment. These results provide a basis on which to use LLMs for classification of student questions. However, we identify clear limitations in both the ability to classify with schemas and the value of doing so: schemas are limited and thus struggle to accommodate the semantic richness of composite prompts, offering only partial understanding the wider risks and benefits of chatbot integration. In the future, we recommend an analysis approach that captures the nuanced, multi-turn nature of conversation, for example, by applying methods from conversation analysis in discursive psychology.