1 citations · 2 across the 8 of their papers we have counts for
8 papers
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
Yipeng Zhao, Qishun Yang, Shenzhe Zhu +2
Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can…
Multi-User Large Language Model Agents
Shu Yang, Shenzhe Zhu, Hao Zhu +5
Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a…
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Songcheng Cai, Zhiheng Lyu, Yuansheng Ni +13
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often over…
HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate
Shenzhe Zhu
Large language models (LLMs) are equipped with safety mechanisms to detect and block harmful queries, yet current alignment approaches primarily focus on overtly dangerous content…
Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs
Shenzhe Zhu, Shu Yang, Michiel A. Bakker +2
Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have be…
Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning
Junchi Yao, Jianhua Xu, Tianyu Xin +4
The rise of Large Language Model-based Multi-Agent Planning has leveraged advanced frameworks to enable autonomous and collaborative task execution. Some systems rely on platforms…
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
Shu Yang, Shenzhe Zhu, Zeyu Wu +7
We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud…
Exploring the Personality Traits of LLMs through Latent Features Steering
Shu Yang, Shenzhe Zhu, Liang Liu +3
Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown…