Kirk Vanacore

Kirk Vanacore, Danielle R Thomas, Digory Smith et al.

This paper introduces a scalable causal inference framework for estimating the immediate, session-level effects of on-demand human tutoring embedded within adaptive learning systems. Because students seek assistance at moments of difficulty, conventional evaluation is confounded by self-selection and time-varying knowledge states. We address these challenges by integrating principled analytic sample construction with Deep Knowledge Tracing (DKT) to estimate latent mastery, followed by doubly robust estimation using Causal Forests. Applying this framework to over 5,000 middle-school mathematics tutoring sessions, we find that requesting human tutoring increases next-problem correctness by approximately 4 percentage points and accuracy on the subsequent skill encountered by approximately 3 percentage points, suggesting that the effects of tutoring have proximal transfer across knowledge components. This effect is robust to various forms of model specification and potential unmeasured confounders. Notably, these effects exhibit significant heterogeneity across sessions and students, with session-level effect estimates ranging from $-20.25pp$ to $+19.91pp$. Our follow-up analyses suggest that typical behavioral indicators, such as student talk time, do not consistently correlate with high-impact sessions. Furthermore, treatment effects are larger for students with lower prior mastery and slightly smaller for low-SES students. This framework offers a rigorous, practical template for the evaluation and continuous improvement of on-demand human tutoring, with direct applications for emerging AI tutoring systems.

Kirk Vanacore, Jaclyn Ocumpaugh, Forest Agostinelli et al.

Games and puzzles play important pedagogical roles in STEM learning. New AI algorithms that can solve complex problems offer opportunities for scaffolded instruction in puzzle solving. This paper presents the ALLURE system, which uses an AI algorithm (DeepCubeA) to guide students in solving a common first step of the Rubik's Cube (i.e., the white cross). Using data from a pilot study we present preliminary findings about students' behaviors in the system, how these behaviors are associated with STEM skills - including spatial reasoning, critical thinking and algorithmic thinking. We discuss how data from ALLURE can be used in future educational data mining to understand how students benefit from AI assistance and collaboration when solving complex problems.

Corina Luca Focsan, Marie Cynthia Abijuru Kamikazi, Tamisha Thompson et al.

Accountable Talk theory has been widely adopted to analyze classroom discourse and is increasingly used to annotate tutoring interactions. In particular, the TalkMoves codebook, grounded in Accountable Talk theory, is commonly used to label tutoring data and train models of effective instructional support. However, Accountable Talk was originally developed to characterize collaborative, whole-classroom oral discourse, not to identify talk moves in one-on-one tutoring environments using multimodal data (e.g., video, audio, chat). As tutoring platforms expand in scale and modality, questions remain about whether Accountable Talk-based codebooks generalize reliably beyond their original classroom context and data representation. This study examines whether the human-developed TalkMoves codebook generalizes in reliability, utility, and interpretability when applied to one-on-one tutoring across audio, chat, and multimodal data. We compare TalkMoves with a hybrid AI-human developed codebook using a workflow established in prior research. Two expert annotators with over 20 years of teaching experience applied both codebooks to six tutoring sessions spanning three modalities: chat-based, audio-only, and multimodal interactions. Results show that while Talk-Moves achieved higher overall inter-rater reliability than the AI-human codebook (k = 0.74 vs. 0.64), the AI-human codebook demonstrated broader empirical coverage and higher perceived usability across modalities. Both codebooks undercaptured tutoring-relevant moves and introduced ambiguity when identifying actions expressed through nonverbal and multimodal artifacts. Together, these findings highlight the uneven generalizability of TalkMoves to tutoring contexts and motivate the development of modality-aware, tutoring-grounded codebooks.

Daryl Hedley, Doug Pietrzak, Jorge Dias et al.

Digital educational environments are expanding toward complex AI and human discourse, providing researchers with an abundance of data that offers deep insights into learning and instructional processes. However, traditional qualitative analysis remains a labor-intensive bottleneck, severely limiting the scale at which this research can be conducted. We present Sandpiper, a mixed-initiative system designed to serve as a bridge between high-volume conversational data and human qualitative expertise. By tightly coupling interactive researcher dashboards with agentic Large Language Model (LLM) engines, the platform enables scalable analysis without sacrificing methodological rigor. Sandpiper addresses critical barriers to AI adoption in education by implementing context-aware, automated de-identification workflows supported by secure, university-housed infrastructure to ensure data privacy. Furthermore, the system employs schema-constrained orchestration to eliminate LLM hallucinations and enforces strict adherence to qualitative codebooks. An integrated evaluations engine allows for the continuous benchmarking of AI performance against human labels, fostering an iterative approach to model refinement and validation. We propose a user study to evaluate the system's efficacy in improving research efficiency, inter-rater reliability, and researcher trust in AI-assisted qualitative workflows.

Zhuqian Zhou, Kirk Vanacore, Bakhtawar Ahtisham et al.

Large-scale sharing of dialogue-based data is instrumental for advancing the science of teaching and learning, yet rigorous de-identification remains a major barrier. In mathematics tutoring transcripts, numeric expressions frequently resemble structured identifiers (e.g., dates or IDs), leading generic Personally Identifiable Information (PII) detection systems to over-redact core instructional content and reduce dataset utility. This work asks how PII can be detected in math tutoring transcripts while preserving their educational utility. To address this challenge, we investigate the "numeric ambiguity" problem and introduce MathEd-PII, the first benchmark dataset for PII detection in math tutoring dialogues, created through a human-in-the-loop LLM workflow that audits upstream redactions and generates privacy-preserving surrogates. The dataset contains 1,000 tutoring sessions (115,620 messages; 769,628 tokens) with validated PII annotations. Using a density-based segmentation method, we show that false PII redactions are disproportionately concentrated in math-dense regions, confirming numeric ambiguity as a key failure mode. We then compare four detection strategies: a Presidio baseline and LLM-based approaches with basic, math-aware, and segment-aware prompting. Math-aware prompting substantially improves performance over the baseline (F1: 0.821 vs. 0.379) while reducing numeric false positives, demonstrating that de-identification must incorporate domain context to preserve analytic utility. This work provides both a new benchmark and evidence that utility-preserving de-identification for tutoring data requires domain-aware modeling.

Bakhtawar Ahtisham, Kirk Vanacore, Zhuqian Zhou et al.

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by LLMs can be used to predict the correctness of a model's own predictions. We analyze 30,300 teacher utterances from classroom dialogue, each labeled by multiple state-of-the-art LLMs with an instructional move construct and an accompanying reasoning. Using human-verified ground-truth labels, we frame the task as predicting whether a model's assigned label for a given utterance is correct. We encode LLM reasoning using Term Frequency-Inverse Document Frequency (TF-IDF) and evaluate five supervised classifiers. A Random Forest classifier achieves an F1 score of 0.83 (Recall = 0.854), successfully identifying most incorrect predictions and outperforming baselines. Training specialist detectors for specific instructional move constructs further improves performance on difficult constructs, indicating that error detection benefits from construct-specific linguistic cues. Using the Linguistic Inquiry and Word Count (LIWC) framework, we examine four linguistic markers of correctness: Causation, Differentiation, Tentativeness, and Insight. Correct predictions exhibit grounded causal language (e.g., because, therefore), while incorrect reasoning is substantially more likely to rely on epistemic hedging (e.g., might, could) and performative metacognition (e.g., think, realize). Syntactic complexity does not distinguish correct from incorrect reasoning, and longer reasoning is not more reliable. These findings demonstrate that reasoning-based error detection offers a practical and scalable approach to quality control in automated educational dialogue analysis.

Bakhtawar Ahtisham, Kirk Vanacore, Jinsook Lee et al.

Large Language Models (LLMs) are increasingly used to annotate learning interactions, yet concerns about reliability limit their utility. We test whether verification-oriented orchestration-prompting models to check their own labels (self-verification) or audit one another (cross-verification)-improves qualitative coding of tutoring discourse. Using transcripts from 30 one-to-one math sessions, we compare three production LLMs (GPT, Claude, Gemini) under three conditions: unverified annotation, self-verification, and cross-verification across all orchestration configurations. Outputs are benchmarked against a blinded, disagreement-focused human adjudication using Cohen's kappa. Overall, orchestration yields a 58 percent improvement in kappa. Self-verification nearly doubles agreement relative to unverified baselines, with the largest gains for challenging tutor moves. Cross-verification achieves a 37 percent improvement on average, with pair- and construct-dependent effects: some verifier-annotator pairs exceed self-verification, while others reduce alignment, reflecting differences in verifier strictness. We contribute: (1) a flexible orchestration framework instantiating control, self-, and cross-verification; (2) an empirical comparison across frontier LLMs on authentic tutoring data with blinded human "gold" labels; and (3) a concise notation, verifier(annotator) (e.g., Gemini(GPT) or Claude(Claude)), to standardize reporting and make directional effects explicit for replication. Results position verification as a principled design lever for reliable, scalable LLM-assisted annotation in Learning Analytics.

Zhuqian Zhou, Kirk Vanacore, Tamisha Thompson et al.

Understanding what makes tutoring effective requires methods for systematically analyzing tutors' instructional actions during learning interactions. This paper presents a tutor move taxonomy designed to support large-scale analysis of tutoring dialogue within the National Tutoring Observatory. The taxonomy provides a structured annotation framework for labeling tutors' instructional moves during one-on-one tutoring sessions. We developed the taxonomy through a hybrid deductive-inductive process. First, we synthesized research from cognitive science, the learning sciences, classroom discourse analysis, and intelligent tutoring systems to construct a preliminary framework of tutoring moves. We then refined the taxonomy through iterative coding of authentic tutoring transcripts conducted by expert annotators with extensive instructional and qualitative research experience. The resulting taxonomy organizes tutoring behaviors into four categories: tutoring support, learning support, social-emotional and motivational support, and logistical support. Learning support moves are further organized along a spectrum of student engagement, distinguishing between moves that elicit student reasoning and those that provide direct explanation or answers. By defining tutoring dialogue in terms of discrete instructional actions, the taxonomy enables scalable annotation using AI, computational modeling of tutoring strategies, and empirical analysis of how tutoring behaviors relate to learning outcomes.

Bakhtawar Ahtisham, Kirk Vanacore, Rene F. Kizilcec

Large language models (LLMs) are increasingly positioned as scalable tools for annotating educational data, including classroom discourse, interaction logs, and qualitative learning artifacts. Their ability to rapidly summarize instructional interactions and assign rubric-aligned labels has fueled optimism about reducing the cost and time associated with expert human annotation. However, growing evidence suggests that single-pass LLM outputs remain unreliable for high-stakes educational constructs that require contextual, pedagogical, or normative judgment, such as instructional intent or discourse moves. This tension between scale and validity sits at the core of contemporary education data science. In this work, we present and empirically evaluate a hierarchical, cost-aware orchestration framework for LLM-based annotation that improves reliability while explicitly modeling computational tradeoffs. Rather than treating annotation as a one-shot prediction problem, we conceptualize it as a multi-stage epistemic process comprising (1) an unverified single-pass annotation stage, in which models independently assign labels based on the rubric; (2) a self-verification stage, in which each model audits its own output against rubric definitions and revises its label if inconsistencies are detected; and (3) a disagreement-centric adjudication stage, in which an independent adjudicator model examines the verified labels and justifications and determines a final label in accordance with the rubric. This structure mirrors established human annotation workflows in educational research, where initial coding is followed by self-checking and expert resolution of disagreements.

Kirk Vanacore, Rene F. Kizilcec

Large language models (LLMs) are increasingly adopted in educational technologies for a variety of tasks, from generating instructional materials and assisting with assessment design to tutoring. While prior work has investigated how models can be adapted or optimized for specific tasks, far less is known about how well LLMs perform at interpreting authentic educational scenarios without significant customization. As LLM-based systems become widely adopted by learners and educators in everyday academic contexts, understanding their out-of-the-box capabilities is increasingly important for setting expectations and benchmarking. We compared six LLMs to estimate their baseline performance on a simple but important task: classifying instructional moves in authentic classroom transcripts. We evaluated typical prompting methods: zero-shot, one-shot, and few-shot prompting. We found that while zero-shot performance was moderate, providing comprehensive examples (few-shot prompting) significantly improved performance for state-of-the-art models, with the strongest configuration reaching Cohen's Kappa = 0.58 against expert-coded annotations. At the same time, improvements were neither uniform nor complete: performance varied considerably by instructional move, and higher recall frequently came at the cost of increased false positives. Overall, these findings indicate that foundation models demonstrate meaningful yet limited capacity to interpret instructional discourse, with prompt design helping to surface capability but not eliminating fundamental reliability constraints.

Jinsook Lee, Kirk Vanacore, Zhuqian Zhou et al.

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.

René Kizilcec, Kirk Vanacore, Zhuqian Zhou et al.

We introduce the Million Tutoring Moves (MTM) project, an open dataset initiative aimed at advancing the science of tutoring through large-scale, reusable, and multimodal interaction data. MTM is developed within the National Tutoring Observatory (NTO), a research infrastructure designed to study authentic tutoring interactions and translate them into actionable insights for research, practice, and AI-powered educational technology development. In this paper, we present the vision behind MTM and describe MTM v1, an initial release consisting of 4,654 math tutoring transcripts from a U.S.-based nonprofit online tutoring platform. MTM v1 serves as a first step toward a broader repository that is safe, open, large-scale, broad-coverage, and multimodal. By making tutoring interactions systematically observable and analyzable, MTM aims to support research on instructional processes, improve tutoring practice, and enable the development of AI systems grounded in real educational interactions.