paper-with-me

홈 › Papers

Chat-Based Support Alone May Not Be Enough: Comparing Conversational and Embedded LLM Feedback for Mathematical Proof Learning

2026-02-21 · Eason Chen, Sophia Judicke, Kayla Beigh, Xinyi Tang, Isabel Wang, Nina Yuan, Zimo Xiao, Chuangji Li, Shizhuo Li, Reed Luttmer, Shreya Singh, Maria Yampolsky, Naman Parikh, Yvonne Zhao, Meiyi Chen, Scarlett Huang, Anishka Mohanty, Gregory Johnson, John Mackey, Jionghao Lin, Ken Koedinger arxiv

We evaluate GPTutor, an LLM-powered tutoring system for an undergraduate discrete mathematics course. It integrates two LLM-supported tools: a structured proof-review tool that provides embedded feedback on students' written proof attempts, and a chatbot for math questions. In a staggered-access study with 148 students, earlier access was associated with higher homework performance during the interval when only the experimental group could use the system, while we did not observe this performance increase transfer to exam scores. Usage logs show that students with lower self-efficacy and prior exam performance used both components more frequently. Session-level behavioral labels, produced by human coding and scaled using an automated classifier, characterize how students engaged with the chatbot (e.g., answer-seeking or help-seeking). In models controlling for prior performance and self-efficacy, higher chatbot usage and answer-seeking behavior were negatively associated with subsequent midterm performance, whereas proof-review usage showed no detectable independent association. Together, the findings suggest that chatbot-based support alone may not reliably support transfer to independent assessment of math proof-learning outcomes, whereas work-anchored, structured feedback appears less associated with reduced learning.

📄 PDF Abstract BibTeX arXiv:2602.18807

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Knowledge-Behaviour Disconnect in LLM-based Chatbots

2025-09-24 · Jan Broersen arxiv

Large language model-based artificial conversational agents (like ChatGPT) give answers to all kinds of questions, and often enough these answers are correct. Just on the basis of that capacity alone, we may attribute kn…

Comparing Generative Chatbots Based on Process Requirements

2023-11-28 · Luis Fernando Lins, Nathalia Nascimento, Paulo Alencar, Toacy Oliveira 외

Business processes are commonly represented by modelling languages, such as Event-driven Process Chain (EPC), Yet Another Workflow Language (YAWL), and the most popular standard notation for modelling business processes,…

Language ModelingLanguage Modelling

Exploring Emotion-Sensitive LLM-Based Conversational AI

2025-02-13 · Antonin Brun, Ruying Liu, Aryan Shukla, Frances Watson 외

Conversational AI chatbots have become increasingly common within the customer service industry. Despite improvements in their emotional development, they often lack the authenticity of real customer service interactions…

ChatbotSentiment Analysis

CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models

2024-02-23 · Juhye Ha, Hyeon Jeon, DaEun Han, Jinwook Seo 외

Large language models (LLMs) have facilitated significant strides in generating conversational agents, enabling seamless, contextually relevant dialogues across diverse topics. However, the existing LLM-driven conversati…

Diversity

Conversational agents for learning foreign languages -- a survey

2020-11-16 · Jasna Petrovic, Mladjan Jovanovic

Conversational practice, while crucial for all language learners, can be challenging to get enough of and very expensive. Chatbots are computer programs developed to engage in conversations with humans. They are designed…

Survey