Imagen de Portada

Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sonkar, Shashank, Liu, Naiming, Baraniuk, Richard G.
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patterns
por: Liu, Naiming, et al.
Publicado: (2025)

CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models
por: Liu, Naiming, et al.
Publicado: (2025)

LLM-based Cognitive Models of Students with Misconceptions
por: Sonkar, Shashank, et al.
Publicado: (2024)

MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education
por: Liu, Naiming, et al.
Publicado: (2024)

Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues
por: Scarlatos, Alexander, et al.
Publicado: (2025)

MalruleLib: Large-Scale Executable Misconception Reasoning with Step Traces for Modeling Student Thinking in Mathematics
por: Chen, Xinghe, et al.
Publicado: (2026)

MetaCLASS: Metacognitive Coaching for Learning with Adaptive Self-regulation Support
por: Liu, Naiming, et al.
Publicado: (2026)

Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits
por: Sonkar, Shashank, et al.
Publicado: (2024)

Many-Shot Regurgitation (MSR) Prompting
por: Sonkar, Shashank, et al.
Publicado: (2024)

Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers
por: Liu, Naiming, et al.
Publicado: (2026)

Pedagogical Alignment of Large Language Models
por: Sonkar, Shashank, et al.
Publicado: (2024)

The Imitation Game for Educational AI
por: Sonkar, Shashank, et al.
Publicado: (2025)

Misconception Acquisition Dynamics in Large Language Models
por: Liu, Naiming, et al.
Publicado: (2026)

Atomic Learning Objectives Labeling: A High-Resolution Approach for Physics Education
por: Liu, Naiming, et al.
Publicado: (2024)

Synthetic Context Generation for Question Generation
por: Liu, Naiming, et al.
Publicado: (2024)

Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation
por: Zengaffinen, Yanick, et al.
Publicado: (2026)

Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors
por: Wang, Jian, et al.
Publicado: (2025)

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
por: Do, Heejin, et al.
Publicado: (2026)

Automated Long Answer Grading with RiceChem Dataset
por: Sonkar, Shashank, et al.
Publicado: (2024)

Scalable Generation and Validation of Isomorphic Physics Problems with GenAI
por: Liu, Naiming, et al.
Publicado: (2026)

Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems
por: Liu, Zhengyuan, et al.
Publicado: (2024)

FoundationalASSIST: An Educational Dataset for Foundational Knowledge Tracing and Pedagogical Grounding of LLMs
por: Worden, Eamon, et al.
Publicado: (2026)

Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
por: Ikram, Fareya, et al.
Publicado: (2025)

Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs
por: Wu, Yang, et al.
Publicado: (2025)

Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs
por: Scarlatos, Alexander, et al.
Publicado: (2024)

Library Learning Doesn't: The Curious Case of the Single-Use "Library"
por: Berlot-Attwell, Ian, et al.
Publicado: (2024)

The Curious Case of Curiosity across Human Cultures and LLMs
por: Borah, Angana, et al.
Publicado: (2025)

Simulated Students in Tutoring Dialogues: Substance or Illusion?
por: Scarlatos, Alexander, et al.
Publicado: (2026)

When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment
por: Ferrer, Robinson, et al.
Publicado: (2026)

Not All Synthetic Data Is Yours to Learn From
por: Alemohammad, Sina, et al.
Publicado: (2026)

A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
por: Dang, Cuong, et al.
Publicado: (2024)

LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
por: Lee, Unggi, et al.
Publicado: (2026)

DeepTutor: Towards Agentic Personalized Tutoring
por: Zhao, Bingxi, et al.
Publicado: (2026)

Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs
por: Purkayastha, Saugata, et al.
Publicado: (2026)

The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text
por: Guo, Yanzhu, et al.
Publicado: (2023)

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
por: Huang, Shuyan, et al.
Publicado: (2026)

The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
por: Lee, Taewhoo, et al.
Publicado: (2025)

Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
por: Duan, Zhangqi, et al.
Publicado: (2026)

Aligning Teacher with Student Preferences for Tailored Training Data Generation
por: Liu, Yantao, et al.
Publicado: (2024)

The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers
por: Islam, Saad Obaid ul, et al.
Publicado: (2025)