Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Lewis et al., Facebook AI  •  Mar 22, 2026  •  10 views

This paper introduces Retrieval-Augmented Generation (RAG), combining parametric memory of pre-trained models with non-parametric memory through a retrieval mechanism over Wikipedia, dramatically impr...

Read Paper
RAG

RLHF: Training Language Models to Follow Instructions with Human Feedback

Ouyang et al., OpenAI  •  Mar 22, 2026  •  2 views

Presents InstructGPT, demonstrating that fine-tuning language models using reinforcement learning from human feedback produces models better aligned with user intent than larger models trained on next...

Read Paper

LLaMA: Open and Efficient Foundation Language Models

Touvron et al., Meta AI  •  Mar 22, 2026  •  1 views

Introduces the LLaMA family of foundation language models ranging from 7B to 65B parameters, trained on publicly available data and outperforming GPT-3 while being more compute-efficient.

Read Paper

The Llama 3 Herd of Models

Meta AI Research  •  Mar 22, 2026  •  1 views

Describes the development of the Llama 3 model family, including a new tokenizer, grouped-query attention, and training on over 15 trillion tokens. Llama 3.1 405B achieves competitive performance with...

Read Paper

Gemini: A Family of Highly Capable Multimodal Models

Gemini Team, Google DeepMind  •  Mar 22, 2026  •  1 views

Presents Gemini, Google DeepMind's multimodal model family trained from the ground up to be natively multimodal across text, images, audio, and video — achieving state-of-the-art performance on 30 o...

Read Paper

Attention Is All You Need (Revisited)

Vaswani et al.  •  Mar 22, 2026  •  30 views

A comprehensive analysis of the transformer architecture five years after its introduction, examining how the original attention mechanism has evolved across modern LLMs.

Read Paper

Constitutional AI: Harmlessness from AI Feedback

Bai et al., Anthropic  •  Mar 22, 2026  •  31 views

This paper introduces Constitutional AI, a method for training harmless AI assistants using AI-generated feedback rather than human labels.

Read Paper

Scaling Laws for Neural Language Models

Kaplan et al., OpenAI  •  Mar 22, 2026  •  32 views

Empirical study of how language model performance scales with model size, dataset size, and compute budget, revealing predictable power-law relationships.

Read Paper