4 papers
LLMCup: Ranking-Enhanced Comment Updating with LLMs
Hua Ge, Juan Zhai, Minxue Pan +2
While comments are essential for enhancing code readability and maintainability in modern software projects, developers are often motivated to update code but not comments, leading…
When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
Huaizhi Ge, Yiming Li, Qifan Wang +2
Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we mo…
How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?
Huaizhi Ge, Frank Rudzicz, Zining Zhu
Large language models (LLMs) have demonstrated remarkable capabilities, but updating their knowledge post-training remains a critical challenge. While recent model editing techniqu…
Understanding Language Model Circuits through Knowledge Editing
Huaizhi Ge, Frank Rudzicz, Zining Zhu
Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these cruci…