4 papers
From Codebases to LLMs: Non-Inclusive Naming in Linux Foundation Repositories
Honghao Tan, Md Nafiu Rahman, Shin Hwei Tan
Since 2020, the Linux Foundation and the multi-organization Inclusive Naming Initiative (INI) have encouraged open-source projects to replace non-inclusive terms such as master/sla…
LLM-Guided Issue Generation from Uncovered Code Segments
Diany Pressato, Honghao Tan, Mariam Elmoazen +1
Developers are increasingly overwhelmed by AI-generated issue reports that lack actionability and reproducibility, eroding trust in automated bug detection tools. In this paper, we…
Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation
Honghao Tan, Haibo Wang, Shin Hwei Tan
Large language models (LLMs) for code generation are typically evaluated on functional correctness alone, overlooking whether generated code propagates harmful content embedded in…
Automated Harmfulness Testing for Code Large Language Models
Honghao Tan, Haibo Wang, Diany Pressato +2
Generative AI systems powered by Large Language Models (LLMs) usually use content moderation to prevent harmful content spread. To evaluate the robustness of content moderation, se…