9 papers
ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles
Yitian Yang, Yiqun Duan, Linghan Huang +4
Large language model (LLM)-based multi-agent simulation offers a powerful testbed for studying social opinion dynamics. Yet current approaches often adopt two contrasting methods:…
Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals
Pengyue Yang, Jiawen Wen, Haolin Jin +3
Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token lik…
Feature-Selective Representation Misdirection for Machine Unlearning
Taozhao Chen, Linghan Huang, Kim-Kwang Raymond Choo +1
As large language models (LLMs) are increasingly adopted in safety-critical and regulated sectors, the retention of sensitive or prohibited knowledge introduces escalating risks, r…
LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models
Linghan Huang, Peizhou Zhao, Huaming Chen
The rapid development of large language models (LLMs) has revolutionized software testing, particularly fuzz testing, by automating the generation of diverse and effective test inp…
NSW-EPNews: A News-Augmented Benchmark for Electricity Price Forecasting with LLMs
Zhaoge Bi, Linghan Huang, Haolin Jin +2
Electricity price forecasting is a critical component of modern energy-management systems, yet existing approaches heavily rely on numerical histories and ignore contemporaneous te…
The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models
Linghan Huang, Haolin Jin, Zhaoge Bi +6
Large language models (LLMs) have seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailb…