activity
20242026
collaborators

8 papers

cs.CL2026

Controlling Chat Style in Language Models via Single-Direction Editing

Zhenyu Xu, Victor S. Sheng

Controlling stylistic attributes in large language models (LLMs) remains challenging, with existing approaches relying on either prompt engineering or post-training alignment. This…

cs.CR2026

A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors

Zhenyu Xu, Victor S. Sheng

Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel finger…

cs.SE2025

CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models

Zhenyu Xu, Victor S. Sheng

The rise of large language models (LLMs) like ChatGPT has significantly improved automated code generation, enhancing software development efficiency. However, this introduces chal…

cs.SE2025

Multi-Task Program Error Repair and Explanatory Diagnosis

Zhenyu Xu, Victor S. Sheng

Program errors can occur in any type of programming, and can manifest in a variety of ways, such as unexpected output, crashes, or performance issues. And program error diagnosis c…

cs.CY2024

Logic Error Localization in Student Programming Assignments Using Pseudocode and Graph Neural Networks

Zhenyu Xu, Kun Zhang, Victor S. Sheng

Pseudocode is extensively used in introductory programming courses to instruct computer science students in algorithm design, utilizing natural language to define algorithmic behav…

cs.SE2024

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT

Zhenyu Xu, Victor S. Sheng

Logical errors in programming don't raise compiler alerts, making them hard to detect. These silent errors can disrupt a program's function or cause run-time issues. Their correcti…