Instruction Following & Finetuning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Foundational papers on teaching language models to follow instructions — from early instruction tuning to modern alignment via supervised finetuning and human feedback.

Instruction Following & Finetuning: 10 key papers

1. Training language models to follow instructions with human feedback
   Ouyang et al. arXiv 2022.
2. Scaling Instruction-Finetuned Language Models
   Chung et al. arXiv 2022.
3. Finetuned Language Models Are Zero-Shot Learners
   Wei et al. arXiv 2021.
4. Multitask Prompted Training Enables Zero-Shot Task Generalization
   Sanh et al. arXiv 2021.
5. Self-Instruct: Aligning Language Models with Self-Generated Instructions
   Wang et al. arXiv 2022.
6. LIMA: Less Is More for Alignment
   Zhou et al. arXiv 2023.
7. Cross-Task Generalization via Natural Language Crowdsourcing Instructions
   Mishra et al. arXiv 2021.
8. Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
   Wang et al. arXiv 2022.
9. Instruction Tuning for Large Language Models: A Survey
   Zhang et al. arXiv 2023.
10. AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
    Dubois et al. arXiv 2023.

Related reading lists

• Vision-Language Models & Multimodal Learning
• RL from Human Feedback (RLHF)
• Preference Learning & Learning from Comparisons
• Zero-Shot RL & Generalization
• Retrieval-Augmented Generation
• Behavioral Cloning & Offline Imitation
• Prompt Optimization & In-Context Learning for LLMs
• AI Alignment & Safety