3 papers
cs.CL2024
Re-Reading Improves Reasoning in Large Language Models
Xiaohan Xu, Chongyang Tao, Tao Shen +5
To enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, Re2, i.e., \textbf{Re}-\text…
cs.CL2024
Adam: Dense Retrieval Distillation with Adaptive Dark Examples
Chongyang Tao, Chang Liu, Tao Shen +4
To improve the performance of the dual-encoder retriever, one effective approach is knowledge distillation from the cross-encoder ranker. Existing works construct the candidate pas…
cs.LG2024
Federated Prompt Learning for Weather Foundation Models on Devices
Shengchao Chen, Guodong Long, Tao Shen +2
On-device intelligence for weather forecasting uses local deep learning models to analyze weather patterns without centralized cloud computing, holds significance for supporting hu…