Your daily digest
Research papers, made simple to understand
The AI and machine learning papers people are reading most, each one rewritten in plain words: the problem, the idea, what was found and why it matters.
- Reinforcement Learning & Alignment
- Language Models & Architectures
Fine-tuning GPT-3 with human feedback improves instruction following and truthfulness
InstructGPT models, fine-tuned from GPT-3 using human demonstrations and preference rankings via reinforcement learning, outperform much larger GPT-3 models in following instructions, truthfulness, and toxicity reduction on diverse tasks.
Paper: Training language models to follow instructions with human feedback · Long Ouyang, Jeff Wu, Xu Jiang and 17 others
Classic · 20226 min readRead the article
- Training & Efficiency
- Language Models & Architectures
LoRA enables efficient fine-tuning of large language models with minimal parameters and no inference latency
LoRA freezes pre-trained weights and trains low-rank update matrices, reducing trainable parameters by up to 10,000× on GPT-3 175B while matching or exceeding full fine-tuning performance on multiple models and tasks.
Paper: LoRA: Low-Rank Adaptation of Large Language Models · Edward J. Hu, Yelong Shen, Phillip Wallis and 5 others
Classic · 20216 min readRead the article
- Language Models & Architectures
- Training & Efficiency
Language model loss follows predictable power laws with size, data, and compute
This paper finds that Transformer language model performance on cross-entropy loss scales as power laws with model size, dataset size, and training compute, enabling optimal compute allocation by training large models on modest data and stopping early.
Paper: Scaling Laws for Neural Language Models · Jared Kaplan, Sam McCandlish, Tom Henighan and 7 others
Classic · 20206 min readRead the article
Browse earlier papers
2 days of papers in November 2026