Picture for Yiping Song

Yiping Song

Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game

Add code
Apr 03, 2024
Viaarxiv icon

LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification

Add code
Feb 26, 2024
Viaarxiv icon

Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation

Add code
Mar 22, 2022
Figure 1 for Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Figure 2 for Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Figure 3 for Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Figure 4 for Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Viaarxiv icon

Trivial bundle embeddings for learning graph representations

Add code
Dec 05, 2021
Figure 1 for Trivial bundle embeddings for learning graph representations
Figure 2 for Trivial bundle embeddings for learning graph representations
Figure 3 for Trivial bundle embeddings for learning graph representations
Figure 4 for Trivial bundle embeddings for learning graph representations
Viaarxiv icon

Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

Add code
May 21, 2021
Figure 1 for Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
Figure 2 for Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
Figure 3 for Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
Figure 4 for Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
Viaarxiv icon

When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications

Add code
May 24, 2020
Figure 1 for When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
Figure 2 for When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
Figure 3 for When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
Viaarxiv icon

Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation

Add code
May 13, 2020
Figure 1 for Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
Figure 2 for Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
Figure 3 for Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
Figure 4 for Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
Viaarxiv icon

Multi-task Learning via Adaptation to Similar Tasks for Mortality Prediction of Diverse Rare Diseases

Add code
May 11, 2020
Figure 1 for Multi-task Learning via Adaptation to Similar Tasks for Mortality Prediction of Diverse Rare Diseases
Figure 2 for Multi-task Learning via Adaptation to Similar Tasks for Mortality Prediction of Diverse Rare Diseases
Figure 3 for Multi-task Learning via Adaptation to Similar Tasks for Mortality Prediction of Diverse Rare Diseases
Figure 4 for Multi-task Learning via Adaptation to Similar Tasks for Mortality Prediction of Diverse Rare Diseases
Viaarxiv icon

Learning to Customize Language Model for Generation-based dialog systems

Add code
Oct 31, 2019
Figure 1 for Learning to Customize Language Model for Generation-based dialog systems
Figure 2 for Learning to Customize Language Model for Generation-based dialog systems
Figure 3 for Learning to Customize Language Model for Generation-based dialog systems
Figure 4 for Learning to Customize Language Model for Generation-based dialog systems
Viaarxiv icon

Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems

Add code
Oct 23, 2016
Figure 1 for Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
Figure 2 for Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
Figure 3 for Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
Figure 4 for Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
Viaarxiv icon