Picture for Kam-Fai Wong

Kam-Fai Wong

DAST: Difficulty-Aware Self-Training on Large Language Models

Add code
Mar 12, 2025
Viaarxiv icon

PEARL: Towards Permutation-Resilient LLMs

Add code
Feb 20, 2025
Viaarxiv icon

Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks

Add code
Feb 10, 2025
Figure 1 for Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
Figure 2 for Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
Figure 3 for Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
Figure 4 for Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
Viaarxiv icon

Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists

Add code
Feb 10, 2025
Figure 1 for Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
Figure 2 for Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
Figure 3 for Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
Figure 4 for Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
Viaarxiv icon

UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models

Add code
Dec 16, 2024
Viaarxiv icon

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis

Add code
Oct 24, 2024
Viaarxiv icon

Analysing the Residual Stream of Language Models Under Knowledge Conflicts

Add code
Oct 21, 2024
Figure 1 for Analysing the Residual Stream of Language Models Under Knowledge Conflicts
Figure 2 for Analysing the Residual Stream of Language Models Under Knowledge Conflicts
Figure 3 for Analysing the Residual Stream of Language Models Under Knowledge Conflicts
Figure 4 for Analysing the Residual Stream of Language Models Under Knowledge Conflicts
Viaarxiv icon

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

Add code
Oct 21, 2024
Figure 1 for Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
Figure 2 for Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
Figure 3 for Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
Figure 4 for Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
Viaarxiv icon

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models

Add code
Oct 16, 2024
Figure 1 for MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Figure 2 for MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Figure 3 for MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Figure 4 for MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Viaarxiv icon

Chain-of-Probe: Examing the Necessity and Accuracy of CoT Step-by-Step

Add code
Jun 23, 2024
Figure 1 for Chain-of-Probe: Examing the Necessity and Accuracy of CoT Step-by-Step
Figure 2 for Chain-of-Probe: Examing the Necessity and Accuracy of CoT Step-by-Step
Figure 3 for Chain-of-Probe: Examing the Necessity and Accuracy of CoT Step-by-Step
Figure 4 for Chain-of-Probe: Examing the Necessity and Accuracy of CoT Step-by-Step
Viaarxiv icon