Picture for Keqing He

Keqing He

DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations

Add code
Mar 31, 2024
Figure 1 for DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
Figure 2 for DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
Figure 3 for DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
Figure 4 for DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
Viaarxiv icon

Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection

Add code
Mar 04, 2024
Figure 1 for Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
Figure 2 for Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
Figure 3 for Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
Figure 4 for Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
Viaarxiv icon

BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses

Add code
Mar 02, 2024
Figure 1 for BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
Figure 2 for BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
Figure 3 for BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
Figure 4 for BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
Viaarxiv icon

PreAct: Predicting Future in ReAct Enhances Agent's Planning Ability

Add code
Feb 18, 2024
Viaarxiv icon

Knowledge Editing on Black-box Large Language Models

Add code
Feb 17, 2024
Figure 1 for Knowledge Editing on Black-box Large Language Models
Figure 2 for Knowledge Editing on Black-box Large Language Models
Figure 3 for Knowledge Editing on Black-box Large Language Models
Figure 4 for Knowledge Editing on Black-box Large Language Models
Viaarxiv icon

Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models

Add code
Feb 17, 2024
Viaarxiv icon

DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning

Add code
Feb 14, 2024
Viaarxiv icon

What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

Add code
Dec 25, 2023
Figure 1 for What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Figure 2 for What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Figure 3 for What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Figure 4 for What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Viaarxiv icon

APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection

Add code
Oct 20, 2023
Figure 1 for APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
Figure 2 for APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
Figure 3 for APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
Figure 4 for APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
Viaarxiv icon

DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task

Add code
Oct 16, 2023
Figure 1 for DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task
Figure 2 for DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task
Figure 3 for DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task
Figure 4 for DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task
Viaarxiv icon