6 papers
FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement
Yinsheng Yao, Hongxiang Zhang, Weixi Tong +1
Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively refine the generated code. Su…
Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
Hongxiang Zhang, Yuan Tian, Tianyi Zhang
LLM-based multi-agent systems have demonstrated remarkable performance on complex tasks through collaborative reasoning. However, these systems tend to rapidly accumulate extremely…
Attention-Aligned Reasoning for Large Language Models
Hongxiang Zhang, Yuan Tian, Tianyi Zhang
Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the origin…
LLAMAFUZZ: Large Language Model Enhanced Greybox Fuzzing
Hongxiang Zhang, Yuyang Rong, Yifeng He +1
Greybox fuzzing has achieved success in revealing bugs and vulnerabilities in programs. However, randomized mutation strategies have limited the fuzzer's performance on structured…
SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
Hongxiang Zhang, Yifeng He, Hao Chen
Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused t…
Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
Hongxiang Zhang, Hao Chen, Muhao Chen +1
Recent decoding methods improve the factuality of large language models (LLMs) by refining how the next token is selected during generation. These methods typically operate at the…