Absolute Zero: Reinforced Self-play Reasoning with Zero Data
learn to reason without any human-annotated data.
Articles in the reference category
-
-
Playing Atari with Deep Reinforcement Learning
a classic paper applying neural networks to RL for game playing
-
Large Language Models are Zero-Shot Reasoners (May 2022)
improve zero-shot prompt performance of LLMs by adding “Let’s think step by step” before each answer
-
Neural Machine Translation by Jointly Learning to Align and Translate (Sep 2014)
improve the Encoder/Decoder alignment with an Attention Mechanism
-
Thinking LLMs: General Instruction Following with Thought Generation (Oct 2024)
a prompting and fine-tuning method that enables LLMs to engage in a "thinking" process before generating responses
-
-
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
a comprehensive evaluation of o1-preview across many tasks and domains.
-
AI Meets the Classroom: When Does ChatGPT Harm Learning?
LLMs can help and also hinder learning outcomes
-
No 'Zero-Shot' Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
a paper that shows a model needs to see a concept exponentially more times to achieve linear improvements
-
Neural Codec Language Models are Zero-Shot Text-to-Speech Synthesizers
VALL-E can generate speech in anyone's voice with only a 3-second sample of the speaker and some text
