16 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…
Optimizing In-Context Demonstrations for LLM-based Automated Grading
Yucheng Chu, Hang Li, Kaiqi Yang +4
Automated assessment of open-ended student responses is a critical capability for scaling personalized feedback in education. While large language models (LLMs) have shown promise…
Confusion-Aware Rubric Optimization for LLM-based Automated Grading
Yucheng Chu, Hang Li, Kaiqi Yang +4
Accurate and unambiguous guidelines are critical for large language model (LLM) based graders, yet manually crafting these prompts is often sub-optimal as LLMs can misinterpret exp…
LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
Yu Zhu, Kai Yang
The reasoning capability of large language models (LLMs), defined as their ability to analyze, infer, and make decisions based on input information, is essential for building intel…