Picture for Liang Ding

Liang Ding

Aligning Large Language Models from Self-Reference AI Feedback with one General Principle

Add code
Jun 17, 2024
Figure 1 for Aligning Large Language Models from Self-Reference AI Feedback with one General Principle
Figure 2 for Aligning Large Language Models from Self-Reference AI Feedback with one General Principle
Figure 3 for Aligning Large Language Models from Self-Reference AI Feedback with one General Principle
Figure 4 for Aligning Large Language Models from Self-Reference AI Feedback with one General Principle
Viaarxiv icon

Uncertainty Aware Learning for Language Model Alignment

Add code
Jun 07, 2024
Viaarxiv icon

Revisiting Catastrophic Forgetting in Large Language Model Tuning

Add code
Jun 07, 2024
Figure 1 for Revisiting Catastrophic Forgetting in Large Language Model Tuning
Figure 2 for Revisiting Catastrophic Forgetting in Large Language Model Tuning
Figure 3 for Revisiting Catastrophic Forgetting in Large Language Model Tuning
Figure 4 for Revisiting Catastrophic Forgetting in Large Language Model Tuning
Viaarxiv icon

Demystifying the Compression of Mixture-of-Experts Through a Unified Framework

Add code
Jun 04, 2024
Figure 1 for Demystifying the Compression of Mixture-of-Experts Through a Unified Framework
Figure 2 for Demystifying the Compression of Mixture-of-Experts Through a Unified Framework
Figure 3 for Demystifying the Compression of Mixture-of-Experts Through a Unified Framework
Figure 4 for Demystifying the Compression of Mixture-of-Experts Through a Unified Framework
Viaarxiv icon

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning

Add code
May 07, 2024
Figure 1 for Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning
Figure 2 for Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning
Figure 3 for Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning
Figure 4 for Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning
Viaarxiv icon

3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset

Add code
Apr 29, 2024
Figure 1 for 3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
Figure 2 for 3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
Figure 3 for 3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
Figure 4 for 3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
Viaarxiv icon

Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Reasoners

Add code
Apr 28, 2024
Figure 1 for Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Reasoners
Figure 2 for Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Reasoners
Figure 3 for Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Reasoners
Figure 4 for Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Reasoners
Viaarxiv icon

Kernel Multigrid: Accelerate Back-fitting via Sparse Gaussian Process Regression

Add code
Mar 30, 2024
Figure 1 for Kernel Multigrid: Accelerate Back-fitting via Sparse Gaussian Process Regression
Figure 2 for Kernel Multigrid: Accelerate Back-fitting via Sparse Gaussian Process Regression
Figure 3 for Kernel Multigrid: Accelerate Back-fitting via Sparse Gaussian Process Regression
Figure 4 for Kernel Multigrid: Accelerate Back-fitting via Sparse Gaussian Process Regression
Viaarxiv icon

Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding

Add code
Mar 27, 2024
Figure 1 for Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
Figure 2 for Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
Figure 3 for Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
Figure 4 for Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
Viaarxiv icon

Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction

Add code
Mar 26, 2024
Figure 1 for Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction
Figure 2 for Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction
Figure 3 for Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction
Figure 4 for Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction
Viaarxiv icon