21 citations · 34 across the 13 of their papers we have counts for
14 papers
GPO: Learning from Critical Steps to Improve LLM Reasoning
Jiahao Yu, Zelei Cheng, Xian Wu +1
Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs have been proposed to improve the \…
Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
Jiahao Yu, Zelei Cheng, Xian Wu +1
Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of…
UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality
Zelei Cheng, Xin-Qiang Cai, Yuting Tang +4
Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to cap…
A Survey on Explainable Deep Reinforcement Learning
Zelei Cheng, Jiahao Yu, Xinyu Xing
Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hin…
Soft-Label Integration for Robust Toxicity Classification
Zelei Cheng, Xian Wu, Jiahao Yu +3
Toxicity classification in textual content remains a significant problem. Data with labels from a single annotator fall short of capturing the diversity of human perspectives. Ther…
UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification
Jiacheng Cai, Jiahao Yu, Yangguang Shao +1
Fingerprinting large language models (LLMs) is essential for verifying model ownership, ensuring authenticity, and preventing misuse. Traditional fingerprinting methods often requi…
BlockScan: Detecting Anomalies in Blockchain Transactions
Jiahao Yu, Xian Wu, Hao Liu +2
We propose BlockScan, a customized Transformer for anomaly detection in blockchain transactions. Unlike existing methods that rely on rule-based systems or directly apply off-the-s…
PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs
Jiahao Yu, Yangguang Shao, Hanwen Miao +1
Large Language Models (LLMs) have gained widespread use in various applications due to their powerful capability to generate human-like text. However, prompt injection attacks, whi…
RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
Zelei Cheng, Xian Wu, Jiahao Yu +3
Deep reinforcement learning (DRL) is playing an increasingly important role in real-world applications. However, obtaining an optimally performing DRL agent for complex tasks, espe…
CAMP: Compiler and Allocator-based Heap Memory Protection
Zhenpeng Lin, Zheng Yu, Ziyi Guo +3
The heap is a critical and widely used component of many applications. Due to its dynamic nature, combined with the complexity of heap management algorithms, it is also a frequent…
ShadowBound: Efficient Heap Memory Protection Through Advanced Metadata Management and Customized Compiler Optimization
Zheng Yu, Ganxiang Yang, Xinyu Xing
In software development, the prevalence of unsafe languages such as C and C++ introduces potential vulnerabilities, especially within the heap, a pivotal component for dynamic memo…
Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries
Jiahao Yu, Haozheng Luo, Jerry Yao-Chieh Hu +3
Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT)…
Assessing Prompt Injection Risks in 200+ Custom GPTs
Jiahao Yu, Yuhang Wu, Dong Shu +3
In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications. The new feature - customization of ChatGPT models by users to ca…
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Jiahao Yu, Xingwei Lin, Zheng Yu +1
Large language models (LLMs) have recently experienced tremendous popularity and are widely used from casual conversations to AI-driven programming. However, despite their consider…