
Wenyue Hua
large language model
benchmark
reasoning
privacy
counterfactual reasoning
language model
model interpretability
ranking
safety
efficient
artifacts
question answering
computational complexity
evaluation benchmark
adversarial attacks
8
presentations
5
number of views
SHORT BIO
Wenyue Hua is a Ph.D. candidate in Computer Science from Rutgers University, specializing in natural language processing and large-language-model-based agents. Her research delves into multi-agent systems, model editing methods, and safety in large foundation models. Her works are published in ICLR, Neurips, EMNLP, TACL, SIGIR, etc.
Presentations

TrustAgent: Towards Safe and Trustworthy LLM-based Agents through Agent Constitution
Wenyue Hua and 6 other authors

BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis
Shuhang Lin and 9 other authors

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
Alfonso Amayuelas and 5 other authors

NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes
Lizhou Fan and 4 other authors

Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks
Wenyue Hua and 5 other authors

The Impact of Reasoning Step Length on Large Language Models
Mingyu Jin and 7 other authors

Discover, Explain, Improve: An Automatic Slice Detection Benchmark for Natural Language Processing
Wenyue Hua and 1 other author

System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning
Wenyue Hua and 1 other author