Picture for Dongfang Li

Dongfang Li

Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment

Add code
Mar 13, 2025
Viaarxiv icon

Improving Value-based Process Verifier via Structural Prior Injection

Add code
Feb 21, 2025
Viaarxiv icon

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model

Add code
Jan 03, 2025
Figure 1 for KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Figure 2 for KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Figure 3 for KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Figure 4 for KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Viaarxiv icon

CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models

Add code
Dec 10, 2024
Figure 1 for CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
Figure 2 for CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
Figure 3 for CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
Figure 4 for CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
Viaarxiv icon

SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation

Add code
Oct 15, 2024
Viaarxiv icon

Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion

Add code
Oct 14, 2024
Figure 1 for Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Figure 2 for Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Figure 3 for Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Figure 4 for Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Viaarxiv icon

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG

Add code
Oct 14, 2024
Viaarxiv icon

In-Context Learning State Vector with Inner and Momentum Optimization

Add code
Apr 17, 2024
Viaarxiv icon

Improving Attributed Text Generation of Large Language Models via Preference Learning

Add code
Mar 27, 2024
Figure 1 for Improving Attributed Text Generation of Large Language Models via Preference Learning
Figure 2 for Improving Attributed Text Generation of Large Language Models via Preference Learning
Figure 3 for Improving Attributed Text Generation of Large Language Models via Preference Learning
Figure 4 for Improving Attributed Text Generation of Large Language Models via Preference Learning
Viaarxiv icon

SelectIT: Selective Instruction Tuning for Large Language Models via Uncertainty-Aware Self-Reflection

Add code
Feb 26, 2024
Figure 1 for SelectIT: Selective Instruction Tuning for Large Language Models via Uncertainty-Aware Self-Reflection
Figure 2 for SelectIT: Selective Instruction Tuning for Large Language Models via Uncertainty-Aware Self-Reflection
Figure 3 for SelectIT: Selective Instruction Tuning for Large Language Models via Uncertainty-Aware Self-Reflection
Figure 4 for SelectIT: Selective Instruction Tuning for Large Language Models via Uncertainty-Aware Self-Reflection
Viaarxiv icon