Výsledky vyhledávání - "Yin, Chengguo"

Report

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors

Autor: Xue, Mengge, Hu, Zhenyu, Liu, Liqun, Liao, Kuo, Li, Shuang, Han, Honglin, Zhao, Meng, Yin, Chengguo

Publikováno v: ACL 2024

Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in MCQs within few-shot scenarios, in which the LLM's performance may be

Externí odkaz: http://arxiv.org/abs/2406.01026

Zobrazit plný text záznamu

Report

Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding

Autor: Liao, Kuo, Li, Shuang, Zhao, Meng, Liu, Liqun, Xue, Mengge, Hu, Zhenyu, Han, Honglin, Yin, Chengguo

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters numerous challen

Externí odkaz: http://arxiv.org/abs/2405.19763

Zobrazit plný text záznamu

Report

VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix

Autor: Wang, Teng, Jiang, Wenhao, Lu, Zhichao, Zheng, Feng, Cheng, Ran, Yin, Chengguo, Luo, Ping

Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors, or crawled from the internet followed by elaborate data cleaning techniques. To reduce the dependen

Externí odkaz: http://arxiv.org/abs/2206.08919

Zobrazit plný text záznamu