Guangyao Zheng — accepted AI-conference papers

2026

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

Zicheng Xu, Xiuyi Lou, Guanchu Wang, Yu-Neng Chuang, Feng Luo, Guangyao Zheng +3

ICML 2026poster

Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to uncover high-quality solutions. To address these limitations, …

Cited by 0 Source ↗Scholar ↗

2025

Self-Ensemble: Mitigating Confidence Distortion for Large Language Models

Zicheng Xu, Guanchu Wang, Guangyao Zheng, Yu-Neng Chuang, Alex Szalay, Xia Hu +1

EMNLP 2025

Although Large Language Models (LLMs) perform well in general fields, they exhibit a **confidence distortion problem** on multi-choice question-answering (MCQA), particularly as the number of answer choices increases. Specifically, on MCQA with many choices, LLMs suffer from under-confidence in corr

Cited by 0 Source ↗PDF ↗Scholar ↗