DISCOVER THE FUTURE OF AI AGENTSarrow_forward

LLMs Paper Reading Club

calendar_todayAdded Feb 22, 2026
categoryDocs, Tutorials & Resources
codeOpen Source
Python大语言模型Knowledge BaseRAGAI AgentsNatural Language ProcessingDocs, Tutorials & ResourcesOtherEducation & Research Resources

A systematic collection of reading notes for LLMs top conference papers, covering motivation and method analysis in core areas like PEFT (LoRA/QLoRA), RAG, and Agents (RoleLLM), providing structured learning paths for algorithm engineers.

Project Overview#

LLMs Paper Reading Club is a knowledge base project maintained by NLP developer 杨夕 (Yang Xi), designed to address the challenge of literature explosion in the Large Language Models field. The project provides structured paper reading notes to help algorithm engineers and researchers quickly grasp the research motivation, core methods, and code implementations of top conference papers.

Use Cases#

  • Technology stack building and interview preparation for LLMs algorithm engineers
  • Quick understanding of SOTA work in Prompt, LoRA, RAG, Agent and other sub-fields
  • Internal team learning sharing and technology selection reference

Core Content Matrix#

PEFT Series (Parameter-Efficient Fine-Tuning)#

TechniqueKey Points
PromptPrompt learning methods for pre-trained language models
InstructionInstruction tuning methods
Self-InstructSelf-generated instruction distillation
LoRALow-Rank Adaptation for LLM fine-tuning with zero inference latency
DyLoRADynamic search-free low-rank adaptation
LOMOFull parameter fine-tuning with limited resources
QLoRA4-bit quantized fine-tuning strategy
VeRAVector-based Random Matrix Adaptation

LoRA Method Details:

  • Motivation: Adapters increase inference latency; Prefix Tuning is hard to optimize with non-monotonic performance
  • Method: Add a bypass to the original model, simulate parameter updates through low-rank decomposition (down-projection matrix A + up-projection matrix B), freeze original model during training, add BA to original parameters during inference with zero additional latency

RAG Series (Retrieval-Augmented Generation)#

TechniqueKey Points
Self-RAGSelf-reflective retrieval-augmented generation
Active RAG (FLARE)Active retrieval-augmented generation
MemSum-DQALong document question answering system
PDFTriageLong structured document QA

Multi-domain Applications: Medical, religious, commonsense, legal, knowledge graphs, task-oriented dialogue, automotive

LLMs Agents Series#

ProjectDescription
RoleLLMRole-playing capability benchmark
Character-LLMTrainable role-playing agents
ChatHaruhiAnime character revival technology
Role-Play with LLMsLarge language model role-playing research

Other Topics#

  • GPT Series: Table parsing, few-shot QA
  • Prompt Series: Few-shot data augmentation methods
  • LMMs Interpretability: LLM factuality survey, self-explanation studies
  • LLMs4KG: ChatKBQA knowledge base QA framework

Knowledge Architecture#

llms_paper/
├── PEFT Series/
│   ├── Prompt / Instruction / Self-Instruct
│   └── LoRA / DyLoRA / LOMO / QLoRA / VeRA
├── GPT Series/
│   └── Table Parsing
├── RAG Series/
│   ├── RAG Tricks
│   └── RAG Applications
├── Prompt Series/
├── LMMs Interpretability/
├── LLMs4KG/
└── LLMs Agents/
    └── Role-Playing

Note Structure Standard#

Each reading note contains:

  • Paper Title and Conference/Source
  • arXiv Link and GitHub Code Link (if available)
  • Core Motivation analysis
  • Methodology diagrams/steps

Usage Guide#

Online Reading#

Visit GitHub repository or Gitee mirror directly

Local Access#

git clone https://github.com/km1994/llms_paper.git

Use Markdown editors (Obsidian, Typora) for local search and reading


Projects maintained by the same author:

  • LLMsNineStoryDemonTower: Systematic LLMs learning path
  • LLMs_interview_notes: LLMs interview question bank
  • NLP-Interview-Notes: Traditional NLP interview notes
  • nlp_paper_study: Early NLP paper notes

Related Projects

View All arrow_forward

STAY UPDATED

Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.

rocket_launch