Yong-Ming Li

CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation

Coding agents can generate code that appears correct but implements behavior the user never intended. This mismatch can arise when an agent silently resolves underspecified requirements through its own assumptions. As subsequent development builds on these assumptions, correcting the resulting behavior can become incre...

Automated Essay Marking with Data-Efficient Augmentation and Score-Token Weighted Loss

Self-Spec Verifiable Code Generation

Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently, researchers have proposed several benchmarks to evaluate the capabilities of LLMs in generating formally verifiable code, where LLMs need to formulat...

Efficient Grammar-Constrained Decoding via Parser Stack Classification

The proposed PSC, a novel grammar-constrained decoding method, can compute the complete vocabulary mask by checking the parser stack exactly once per decoding step, with time complexity independent of the vocabulary size.