Picture for Sungjin Lee

Sungjin Lee

Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language

Add code
Nov 24, 2023
Figure 1 for Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language
Figure 2 for Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language
Figure 3 for Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language
Figure 4 for Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language
Viaarxiv icon

Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems

Add code
Jun 07, 2023
Figure 1 for Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems
Figure 2 for Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems
Figure 3 for Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems
Figure 4 for Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems
Viaarxiv icon

Open World Classification with Adaptive Negative Samples

Add code
Mar 09, 2023
Figure 1 for Open World Classification with Adaptive Negative Samples
Figure 2 for Open World Classification with Adaptive Negative Samples
Figure 3 for Open World Classification with Adaptive Negative Samples
Figure 4 for Open World Classification with Adaptive Negative Samples
Viaarxiv icon

Cluster-Guided Label Generation in Extreme Multi-Label Classification

Add code
Feb 17, 2023
Figure 1 for Cluster-Guided Label Generation in Extreme Multi-Label Classification
Figure 2 for Cluster-Guided Label Generation in Extreme Multi-Label Classification
Figure 3 for Cluster-Guided Label Generation in Extreme Multi-Label Classification
Figure 4 for Cluster-Guided Label Generation in Extreme Multi-Label Classification
Viaarxiv icon

Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information

Add code
Feb 10, 2023
Figure 1 for Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Figure 2 for Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Figure 3 for Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Figure 4 for Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Viaarxiv icon

Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems

Add code
Sep 17, 2022
Figure 1 for Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems
Figure 2 for Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems
Figure 3 for Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems
Figure 4 for Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems
Viaarxiv icon

Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems

Add code
Aug 18, 2022
Figure 1 for Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
Figure 2 for Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
Figure 3 for Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
Figure 4 for Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
Viaarxiv icon

Learning Personalized Representations using Graph Convolutional Network

Add code
Jul 28, 2022
Figure 1 for Learning Personalized Representations using Graph Convolutional Network
Figure 2 for Learning Personalized Representations using Graph Convolutional Network
Figure 3 for Learning Personalized Representations using Graph Convolutional Network
Figure 4 for Learning Personalized Representations using Graph Convolutional Network
Viaarxiv icon

Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems

Add code
Apr 14, 2022
Figure 1 for Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems
Figure 2 for Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems
Figure 3 for Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems
Figure 4 for Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems
Viaarxiv icon

Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data

Add code
Apr 05, 2022
Figure 1 for Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data
Figure 2 for Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data
Figure 3 for Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data
Figure 4 for Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data
Viaarxiv icon