4 citations · 4 across the 4 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023
AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation
Junjie Wang, Yicheng Chen, Wangshu Zhang +3
Leveraging knowledge from multiple tasks through introducing a small number of task specific parameters into each transformer layer, also known as adapters, receives much attention…
cs.SE2023
Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning
Yinger Zhang, Hui Cai, Xeirui Song +3
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…