Picture for Dayuan Fu

Dayuan Fu

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

Mar 31, 2024
Viaarxiv icon

On Large Language Models' Hallucination with Regard to Known Facts

Mar 29, 2024
Figure 1 for On Large Language Models' Hallucination with Regard to Known Facts
Figure 2 for On Large Language Models' Hallucination with Regard to Known Facts
Figure 3 for On Large Language Models' Hallucination with Regard to Known Facts
Figure 4 for On Large Language Models' Hallucination with Regard to Known Facts
Viaarxiv icon

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

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

A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER

Add code
Aug 28, 2023
Viaarxiv icon

A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition

Feb 27, 2023
Figure 1 for A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition
Figure 2 for A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition
Figure 3 for A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition
Figure 4 for A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition
Viaarxiv icon

Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations

Feb 27, 2023
Figure 1 for Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations
Figure 2 for Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations
Figure 3 for Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations
Figure 4 for Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations
Viaarxiv icon

Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems

Add code
Oct 17, 2022
Figure 1 for Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
Figure 2 for Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
Figure 3 for Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
Figure 4 for Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
Viaarxiv icon