← Search

Che-Yu Lin

2 accepted papers

2025

Beyond Oracle: Verifier-Supervision for Instruction Hierarchy in Reasoning and Instruction-Tuned LLMs

NeurIPS 2025poster

Large language models (LLMs) are often prompted with multi-level directives, such as system instructions and user queries, that imply a hierarchy of authority. Yet models frequently fail to enforce this structure, especially in multi-step reasoning where errors propagate across intermediate steps. E…

Cited by 0SourcecodeScholar
2024

CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Research

EMNLP 2024main

This research addresses command-line embedding in cybersecurity, a field obstructed by the lack of comprehensive datasets due to privacy and regulation concerns. We propose the first dataset of similar command lines, named CyPHER, for training and unbiased evaluation. The training set is generated u…