8 papers
Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation
Kaiqi Yang, Tai-Quan Peng, Sanguk Lee +1
LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics. However, many existing dialogue simulation frame…
"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems
Hang Li, Fedor Filippov, Yuping Lin +6
The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-foll…
From Flat to Structural: Enhancing Automated Short Answer Grading with GraphRAG
Yucheng Chu, Haoyu Han, Shen Dong +6
Automated short answer grading (ASAG) is critical for scaling educational assessment, yet large language models (LLMs) often struggle with hallucinations and strict rubric adherenc…
Iterative LLM-Based Generation and Refinement of Distracting Conditions in Math Word Problems
Kaiqi Yang, Hang Li, Yucheng Chu +3
Mathematical reasoning serves as a crucial testbed for the intelligence of large language models (LLMs), and math word problems (MWPs) are a popular type of math problems. Most MWP…
Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
Hang Li, Kaiqi Yang, Yucheng Chu +2
Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or…
A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics Teachers
Kaiqi Yang, Hang Li, Yucheng Chu +4
Professional development (PD) serves as the cornerstone for teacher tutors to grasp content knowledge. However, providing equitable and timely PD opportunities for teachers poses s…