LLM-Performance-Improvement-Paper

Overview

Paper List

[1] Scale laws

[2] Diversity & Quality

• LIMA : Less Is More for Alignment
• Textbooks are all you need

[3] Filter Model

• Textbooks are all you need
• GPT3:Language Models are Few-Shot Learners

[4][5] Teacher Model & Zero shot labelling

• Textbooks are all you need
• GPT Self-Supervision for a Better Data Annotator

[6] Reward Model

• Lets Verify Step by Step

[7] RLHF or DPO

• Training language models to follow instructions with human feedback
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Scaling Laws for Reward Model Overoptimization
• AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
• RRHF: Rank Responses to Align Language Models with Human Feedback without tears

[8] Instruct Understanding & Prompt-Answer Matching

• Training language models to follow instructions with human feedback
• LIMA : Less Is More for Alignment
• The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
• Scaling Instruction-Finetuned Language Models

[9] Self Instruct from GPT

• Aligning Language Models with Self-Generated Instructions
• SELF-INSTRUCT: Aligning Language Models with Self-Generated Instructions
• Wizardlm: Empowering large language models to follow complex instructions
• WizardCoder: Empowering Code Large Language Models with Evol-Instruct
• Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation
• Alpaca: A Strong Replicable Instruction-Following Model
• How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

[10] Principle-Driven Alignment:

• Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision