Yinger Zhang — accepted AI-conference papers

2024

MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts

Zhitian Xie, Yinger Zhang, Chenyi Zhuang, Qitao Shi, Zhining Liu, Jinjie Gu +1

AAAI 2024technical

The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model's performance. In an MoE structure, the gate layer plays a significant role in distinguishing and routing input features to different experts. This enables each expert to specialize in processing t…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2024

Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning

Yinger Zhang, Hui Cai, Xierui Song, Yicheng Chen, Rui Sun, Jing Zheng

NAACL 2024findings

While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting witho…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗