The paper introduces an educator‑guided large language model (LLM) pedagogical agent that provides scaffolded feedback for conceptual database design. Embedded in an entity–relationship diagram editor, the system bases its feedback on the student’s artifact, assignment requirements, educator‑authored rubrics, and instructional resources, using a four‑stage workflow that progresses from concept checks to low‑detail feedback and localized clarification. In a deployment across three ERD environments with 383 feedback episodes, 71.1% of target‑level changes incorporated the hidden diagnostic target, and qualitative analysis highlighted the benefits and challenges of staged disclosure.
Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments. Yet serious cases are scarce, records rarely contain reasoning paths, and data transfer poorly across configurations, complicating local deployment.
The article examines how Large Language Models can aid in creating Entity-Relationship diagrams from natural language requirements. It tests three LLMs with three prompting strategies—Zero-Shot, Chain of Thought, and Chain of Thought + Verifier—on scenarios of increasing complexity. Findings show that while LLMs perform adequately on simpler tasks, their reliability drops with more complex requirements, leading to inconsistencies, ambiguities, and constraint representation failures.
arXiv:2608. 03674v1 Announce Type: new Abstract: Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments.
arXiv:2606. 17507v1 Announce Type: new Abstract: Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment.
RegulaTutor is a theory-informed framework for long‑term personalized tutoring that links a learner’s historical evidence to instructional support. Guided by self‑regulated learning research, it uses a cognitive, affective, metacognitive, and motivational (CAMM) framework to derive evidence‑supported learner interpretations and teaching policies that are updated as new observations arrive. The framework includes PairRoute, an offline refinement procedure that distinguishes harness, model, and mixed failures, proposes targeted harness revisions, and constructs stage‑level supervision for confirmed model failures, improving historical‑evidence accuracy, learner diagnosis, and teaching quality across evaluated model configurations.
arXiv:2607. 14707v1 Announce Type: cross Abstract: Large language models routinely produce fluent answers to single-shot prompts, yet deploying them as reliable components of a domain decision system is substantially harder.
arXiv:2512. 10785v3 Announce Type: replace-cross Abstract: Generative AI offers new opportunities for individualized and adaptive learning, e.
arXiv:2608. 08254v1 Announce Type: new Abstract: Structured output, where an LLM populates a predefined JSON schema, has become a default mechanism for data labeling and information extraction, but it also introduces a second instruction channel through schema descriptions.
The paper examines whether state‑of‑the‑art large language models (LLMs) produce feedback that aligns with expert teachers’ pedagogical practices, focusing on feedback type and adaptivity. Using a refined taxonomy of seven feedback focus types, the authors annotate and compare teacher and LLM‑generated feedback from three university writing courses, creating the FeedType benchmark. Their analysis shows that while most LLMs cover many feedback types, they do not match teachers’ distribution patterns or adaptive behavior across draft stages and student performance levels.
arXiv:2607. 16851v1 Announce Type: new Abstract: Deploying LLM agents typically requires a compact test-time student, even if a stronger teacher is available during training.
The study analyzes 20,462 student turns from 1,260 sessions with a guided LLM chemistry tutor, identifying 6,630 impasse turns categorized as conceptual errors, expressed uncertainty, or help‑seeking. Three tutoring conditions—baseline, no‑direct‑answer, and guided—were simulated, revealing that the baseline tutor often gave direct answers, the no‑direct‑answer tutor always asked follow‑up questions, and the guided tutor varied its responses based on context. Impasse trajectories showed that each additional impasse turn reduced the likelihood of recovery, while addressing errors became increasingly beneficial compared to repeated scripted questioning.
arXiv:2605. 05598v2 Announce Type: replace Abstract: The proliferation of large language models (LLMs) in educational settings has paradoxically undermined the cognitive processes they purport to support.