Nathan Lambert, Ph.D.
Allen Institute for AI (Ai2)
Staff Research Scientist at the Allen Institute for AI (Ai2) and author of the acclaimed newsletter Interconnects. Lead scientist on the open-source Tülu 3 post-training project and RewardBench, pioneering transparent, fully reproducible RLHF, Direct Preference Optimization (DPO), and verifiable reasoning alignment.
Areas of focus
Professional niches
Proof of Work
RewardBench: Evaluating Reward Models for Language Model Alignment
Created RewardBench, the industry's primary benchmark for evaluating reward models and preference classifiers across chat capabilities, reasoning, and adversarial safety edge cases.
Static evaluation test sets face saturation as training data mixtures incorporate benchmark distributions.
Context: Evaluation suite assessing over 100 reward models across Chat, Reasoning, and Safety axes.
View missionTülu 3: Pushing Frontiers in Open Language Model Post-Training
Co-led the Tülu 3 open post-training initiative, releasing complete training datasets, recipes, and checkpoint weights demonstrating open-source parity with proprietary frontier models through RLVR and DPO.
Verifiable rewards require deterministic verifiers (math/code compilers), limiting RLVR application in subjective writing.
Context: Llama 3.1 base models, Direct Preference Optimization, Reinforcement Learning from Verifiable Rewards (RLVR).
View mission