Open Instruct: A Simple Method for Aligning Language Models with Human Preferences

Yizhong Wang is a research scientist at the Allen Institute for AI and incoming assistant professor at the University of Washington whose work focuses on language models, agents, reasoning, and open-source AI.

Noah A. Smith is a computer scientist and professor at the University of Washington, where he serves as Vice Provost for Artificial Intelligence and co-directs the OLMo open language modeling effort with Ai2. His research focuses on natural language processing, machine learning, and evaluation methodology.

Saumya Malik is an incoming postdoctoral scholar at Johns Hopkins University and recently completed a PhD in the Machine Learning Department at Carnegie Mellon University. Her interests include interpretability, evaluation, reward learning, and language model agents.

Thomas Scialom is a research scientist at Ai2. His work focuses on reasoning, data quality, and post-training for language models.

AI2 researcher working on multimodal language models, evaluations, instruction tuning, and preference alignment, and a co-author of Open Instruct.

Allen Institute for AI researcher working on NLP, machine learning, and AI, and a co-author of Open Instruct.

Research scientist at the Allen Institute for AI focused on training, evaluating, and interpreting language models, with work spanning NLP and computational social science.

Machine learning scientist at Ai2 working on reinforcement learning, language models, and online social systems.

Senior research scientist at Ai2 and associate professor at Yale working on long-form language understanding, information retrieval, and scientific NLP.

Machine learning engineer at Ai2 whose public work focuses on open language models, post-training, and evaluation.

Research engineer at Ai2 working on open language models, machine learning systems, and evaluation.

Profile still being enriched.

Profile still being enriched.

Profile still being enriched.

Profile still being enriched.

Profile still being enriched.

Profile still being enriched.

Profile still being enriched.

Profile still being enriched.