5 papers
Process In-Context Learning: Enhancing Mathematical Reasoning via Dynamic Demonstration Insertion
Ang Gao, Changshuo Zhang, Xiao Zhang +4
In-context learning (ICL) has proven highly effective across diverse large language model (LLM) tasks. However, its potential for enhancing tasks that demand step-by-step logical d…
ADOPT: Adaptive Dependency-Guided Joint Prompt Optimization for Multi-Step LLM Pipelines
Minjun Zhao, Xinyu Zhang, Shuai Zhang +2
Multi-step LLM pipelines can solve complex tasks, but jointly optimizing prompts across steps remains challenging due to missing step-level supervision and inter-step dependency. W…
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
Xiang Cheng, Chengyan Pan, Minjun Zhao +5
In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs), and recent studies introduce Chain-of-Thought (CoT) to exemplars of ICL to enhance the r…
SparDL: Distributed Deep Learning Training with Efficient Sparse Communication
Minjun Zhao, Yichen Yin, Yuren Mao +3
Top-k sparsification has recently been widely used to reduce the communication volume in distributed deep learning. However, due to the Sparse Gradient Accumulation (SGA) dilemma,…
Finding Materialized Models for Model Reuse
Minjun Zhao, Lu Chen, Keyu Yang +2
Materialized model query aims to find the most appropriate materialized model as the initial model for model reuse. It is the precondition of model reuse, and has recently attracte…