activity
20192023
most citedLanguage Models as Few-Shot Learner for Task-Oriented Dialogue Systems

36 citations · 136 across the 17 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.CL2022★ 5 cited

RHO (): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

Ziwei Ji, Zihan Liu, Nayeon Lee +4

Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce halluci…

cs.CL2022★ 2 cited

Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training

Wenliang Dai, Zihan Liu, Ziwei Ji +2

Large-scale vision-language pre-trained (VLP) models are prone to hallucinate non-existent visual objects when generating text based on visual information. In this paper, we system…

cs.CL2022★ 1 cited

Effective Transfer Learning for Low-Resource Natural Language Understanding

Zihan Liu

Natural language understanding (NLU) is the task of semantic decoding of human languages by machines. NLU models rely heavily on large training data to ensure good performance. How…

cs.CL2022★ 10 cited

Mere Contrastive Learning for Cross-Domain Sentiment Analysis

Yun Luo, Fang Guo, Zihan Liu +1

Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data.…

cs.LG2022

SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study

Samuel Cahyawijaya, Tiezheng Yu, Zihan Liu +4

Self-supervised pre-training methods have brought remarkable breakthroughs in the understanding of text, image, and speech. Recent developments in genomics has also adopted these p…