← Search

Runcheng Liu

2 accepted papers

2023

Attribute Controlled Dialogue Prompting

ACL 2023findings

Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data samples within a task, neglecting the fact that inputs vary great…

Cited by 4SourcePDFScholar
2022

PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding

NeurIPS 2022accept

We are now witnessing significant progress of deep learning methods in a variety of tasks (or datasets) of proteins. However, there is a lack of a standard benchmark to evaluate the performance of different methods, which hinders the progress of deep learning in this field. In this paper, we propose…