Picture for Zhicheng Dou

Zhicheng Dou

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning

Add code
Nov 06, 2024
Viaarxiv icon

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Add code
Nov 05, 2024
Viaarxiv icon

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation

Add code
Oct 30, 2024
Viaarxiv icon

Little Giants: Synthesizing High-Quality Embedding Data at Scale

Add code
Oct 24, 2024
Viaarxiv icon

A Survey of Conversational Search

Add code
Oct 21, 2024
Viaarxiv icon

Toward General Instruction-Following Alignment for Retrieval-Augmented Generation

Add code
Oct 12, 2024
Viaarxiv icon

LLMs + Persona-Plug = Personalized LLMs

Add code
Sep 18, 2024
Viaarxiv icon

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

Add code
Sep 16, 2024
Viaarxiv icon

MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery

Add code
Sep 10, 2024
Figure 1 for MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery
Figure 2 for MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery
Figure 3 for MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery
Figure 4 for MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery
Viaarxiv icon

Towards Effective and Efficient Continual Pre-training of Large Language Models

Add code
Jul 26, 2024
Figure 1 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Figure 2 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Figure 3 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Figure 4 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Viaarxiv icon