Olga Golovneva

StepWiser: Stepwise Generative Judges for Wiser Reasoning

The Era of Real-World Human Interaction: RL from User Conversations

CoT-Self-Instruct: Building high-quality synthetic prompts data for reasoning and non-reasoning tasks

Multi-Token Attention

Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models

Contextual Position Encoding: Learning to Count What’s Important

Self-Taught Evaluators

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

R.I.P.: Better Models by Survival of the Fittest Prompts