LLM benchmarks, agent evaluations, and experiments.
-
ResearchLost in the Middle: How LLMs Use Long Contexts
Introduction This paper examines how well language models utilize longer input contexts. The study focuses on multi-document question answering and key-value retrieval tasks. The researchers find that performance… Sarah Welsh July 25, 2023 41 min read -
Research
Orca: Progressive Learning from Complex Explanation Traces of GPT-4 Paper Reading
Introduction Recent research focuses on improving smaller models through imitation learning using outputs from large foundation models (LFMs). Challenges include limited imitation signals, homogeneous training data, and a… Sarah Welsh July 13, 2023 30 min read -
Research
One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning
Introduction In this week’s paper reading, we discuss “One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning.” GLoRA is a universal, parameter-efficient fine-tuning approach for diverse tasks. It enhances LoRA with… Sarah Welsh July 3, 2023 32 min read -
Research
HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels
Introduction In this paper reading, we explore HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels. HyDE is a thrilling zero-shot learning technique that combines GPT-3’s language understanding with… Sarah Welsh June 27, 2023 30 min read -
Research
Voyager: An Open-Ended Embodied Agent with LLMs Paper Reading and Discussion
Introduction In this paper reading, we discuss Voyager: the first LLM-powered embodied lifelong learning agent in Minecraft. Voyager autonomously explores the world, acquires skills, and makes discoveries without… Sarah Welsh June 19, 2023 31 min read -
Research
LoRA: Low-Rank Adaptation of Large Language Models Paper Reading and Discussion
Introduction In this paper reading, we discuss LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly… Sarah Welsh June 12, 2023 28 min read -
Research
Retrieval-Augmented Generation – Paper Reading and Discussion
Introduction In this paper reading, we discuss “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” We know GPT-like LLMs are great at soaking up knowledge during pre-training and fine-tuning them… Sarah Welsh June 9, 2023 34 min read -
Research
LIMA: Less Is More for Alignment – Paper Reading and Discussion
Introduction In this paper reading, we discuss “LIMA: Less Is More for Alignment.” This research delves into the efficiency and effectiveness of large language models, demonstrating the power… Sarah Welsh June 1, 2023 25 min read -
Research
Drag Your GAN: Interactive Point-Based Manipulation on the Generative Image Manifold
Introduction In this paper reading, we dive into “Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold.” Drag Your GAN introduces a novel approach for achieving… Sarah Welsh June 1, 2023 23 min read
Don’t ship vibes.
Arize gives AI teams observability and evals to understand and improve agent performance.
