Recent AI Reading [20 July 2024]
Papers
- LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models
- GenAI Arena: An Open Evaluation Platform for Generative Models | GenAI-Arena
- Matching Anything by Segmenting Anything
- Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
- Nemotron-4 340B Technical Report - Nvidia
- Creativity Has Left the Chat: The Price of Debiasing Language Models
- Rich Human Feedback for Text-to-Image Generation
- Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered Applications
- Prover-Verifier Games improve legibility of LLM outputs
- Corresponding article at OpenAI: Prover-Verifier Games improve legibility of language model outputs
Articles and Blog Posts
- Large Language Model Evaluation in 2024: 5 Methods
- Finding GPT-4’s mistakes with GPT-4
- A new initiative for developing third-party model evaluations
- Can LLMs invent better ways to train LLMs?
- Notes on how to use LLMs in your product.