Jiaxin Zhang

PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback

2023 · arXiv (Cornell University)

Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task. Various approaches have been proposed to boost the …

SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable

2025 · arXiv (Cornell University)

Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate reliable responses …