activity
20242026
collaborators

5 papers

cs.AI2026

Interpreting and Steering for Safe and Correct Code Generation

Hao Yan, Ziyu Yao

Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguish safe from vulnerable gener…

cs.AI2026

Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective

Mohamed Aghzal, Gregory J. Stein, Ziyu Yao

Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus pr…

cs.SE2025

Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation

Hao Yan, Swapneel Suhas Vaidya, Xiaokuan Zhang +1

Large Language Models have become powerful tools for programming. However, they often overlook essential security practices, producing insecure code with vulnerabilities. Despite t…

cs.CL2025

Can LLMs Simulate Personas with Reversed Performance? A Systematic Investigation for Counterfactual Instruction Following in Math Reasoning Context

Sai Adith Senthil Kumar, Hao Yan, Saipavan Perepa +2

Large Language Models (LLMs) are now increasingly widely used to simulate personas in virtual environments, leveraging their instruction-following capability. However, we discovere…

cs.HC2024

IntelliExplain: Enhancing Conversational Code Generation for Non-Professional Programmers

Hao Yan, Thomas D. Latoza, Ziyu Yao

Chat LLMs such as GPT-3.5-turbo and GPT-4 have shown promise in assisting humans in coding, particularly by enabling them to conversationally provide feedback. However, current app…