9 papers
Understanding and Improving Model Editing for Secure Code Generation
Weifeng Sun, Quanjun Zhang, Yuchen Chen +3
Large language models (LLMs) are widely used for code generation, yet they can reproduce vulnerable implementations learned from insecure training patterns. Prior work has mainly e…
How Reasoning Shapes Social Bias in LLM-Generated Code?
Weifeng Sun, Jieke Shi, Zhou Yang +4
Large language models (LLMs) are increasingly used for code generation, yet generated programs may exhibit social bias through unfair or differential treatment of sensitive demogra…
AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection
Gou Tan, Zhensu Sun, Jieke Shi +10
Agent systems rely on LLM APIs for every response, but these APIs can return server errors, truncated responses, or corrupted content that propagates through downstream agents and…
Lossless Tensor Compression as Program Synthesis
Jieke Shi, Junda He, Wenjia Jiang +11
Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requiremen…
SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation
Weifeng Sun, Ye Fan, Yuchen Chen +6
Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question. Existing datasets and benchmarks are limit…
Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation
Yuchen Chen, Wei Cheng, Yuan Xiao +7
LLM-based systems increasingly incorporate long-term memory to improve cross-session continuity. However, once insecure coding preferences are stored, they may silently influence s…