Publications

2026

Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving

Hang Li, Kaiqi Yang, Yucheng Chu, Hui Liu, Jiliang Tang

The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), , 2026

[Preprint]

Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving

Hang Li, Kaiqi Yang, Yucheng Chu, Hui Liu, Jiliang Tang

The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), , 2026

[Preprint]

Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems
Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

Hang Li*, Fedor Filippov*, Yuping Lin, Pengfei He, Kaiqi Yang, Yucheng Chu, Yingqian Cui, Hui Liu, Jiliang Tang (* equal contribution)

The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), , 2026

[Preprint]

Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

Hang Li*, Fedor Filippov*, Yuping Lin, Pengfei He, Kaiqi Yang, Yucheng Chu, Yingqian Cui, Hui Liu, Jiliang Tang (* equal contribution)

The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), , 2026

[Preprint]

Designing Professional Development in Mathematics Teacher Education with AI as a Facilitator
A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics Teachers
Optimizing In-Context Demonstrations for LLM-based Automated Grading
From Flat to Structural: Enhancing Automated Short Answer Grading with GraphRAG
Confusion-Aware Rubric Optimization for LLM-based Automated Grading
Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models

2025

Iterative LLM-Based Generation and Refinement of Distracting Conditions in Math Word Problems
LLM-based Automated Grading with Human-in-the-Loop
Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions
Bringing Generative Artificial Intelligence (GenAI) to Education
A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization

2024

Are Large Language Models (LLMs) Good Social Predictors?
Content Knowledge Identification with Multi-Agent Large Language Models (LLMs)

2023

Spectral-Aware Augmentation for Enhanced Graph Representation Learning

Preprints

2026

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation
Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation

Kaiqi Yang, Tai-Quan Peng, Sanguk Lee, Hui Liu

arXiv preprint arXiv:2606.03137 , 2026 (presented at KDD'26 Workshop on Agentic AI for Scientific and Societal Advances)

[Preprint]

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation

Kaiqi Yang, Tai-Quan Peng, Sanguk Lee, Hui Liu

arXiv preprint arXiv:2606.03137 , 2026 (presented at KDD'26 Workshop on Agentic AI for Scientific and Societal Advances)

[Preprint]

How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment

2025

Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation

2024

Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations

All cover images on this page are generated by Seedream of Doubao.