Picture for Feiyu Xiong

Feiyu Xiong

$\text{Memory}^3$: Language Modeling with Explicit Memory

Add code
Jul 01, 2024
Viaarxiv icon

HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability

Add code
Jun 30, 2024
Viaarxiv icon

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models

Add code
Jun 23, 2024
Viaarxiv icon

Improving Generalization and Convergence by Enhancing Implicit Regularization

Add code
May 31, 2024
Viaarxiv icon

Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning

Add code
May 27, 2024
Viaarxiv icon

xFinder: Robust and Pinpoint Answer Extraction for Large Language Models

Add code
May 23, 2024
Viaarxiv icon

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy

Add code
Mar 07, 2024
Figure 1 for Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Figure 2 for Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Figure 3 for Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Figure 4 for Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Viaarxiv icon

NewsBench: Systematic Evaluation of LLMs for Writing Proficiency and Safety Adherence in Chinese Journalistic Editorial Applications

Add code
Feb 29, 2024
Figure 1 for NewsBench: Systematic Evaluation of LLMs for Writing Proficiency and Safety Adherence in Chinese Journalistic Editorial Applications
Figure 2 for NewsBench: Systematic Evaluation of LLMs for Writing Proficiency and Safety Adherence in Chinese Journalistic Editorial Applications
Figure 3 for NewsBench: Systematic Evaluation of LLMs for Writing Proficiency and Safety Adherence in Chinese Journalistic Editorial Applications
Figure 4 for NewsBench: Systematic Evaluation of LLMs for Writing Proficiency and Safety Adherence in Chinese Journalistic Editorial Applications
Viaarxiv icon

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs

Add code
Feb 17, 2024
Viaarxiv icon

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

Add code
Jan 30, 2024
Viaarxiv icon