Abe Hou
I am a PhD student in Computer Science at Stanford University, working with Chris Manning, Diyi Yang, and Dan Ho. I am interested in understanding how people can supervise and build AI systems in non-verifiable domains (such as scientific discovery and law). I believe when models work in non-verifiable domains, we need to ensure: I graduated from Johns Hopkins University with a B.S. in Computer Science and Mathematics. I am extremely grateful to have worked with Ben Van Durme, Daniel Khashabi, and Tianxing He.
Abe Bohan Hou Stanford CS · PhD 2025— Hi! I am Abe Hou. I am a PhD student in Computer Science at Stanford University, working with James Zou, Chris Manning, Dan Ho, and Diyi Yang. I am interested in understanding how people can supervise and build AI systems in non-verifiable domains (such as scientific discovery and law), with focuses on process validation and diversity. I graduated from Johns Hopkins University with a B.S. in Computer Science and Mathematics. I am extremely grateful to have worked with Ben Van Durme, Daniel Khashabi, and Tianxing He. Publications Reasoning in…
saved by
related reading
- Trending Papers - Hugging Facepaperswithcode.com
- Oversight Assistants: Turning Compute into Understandingbounded-regret.ghost.io
- Import AIjack-clark.net
- Group | Sherry Tongshuang Wucs.cmu.edu
- Publicationseilab.gatech.edu
- Training a State-of-the-Art Legal Agent with Harvey | Applied Computeappliedcompute.com
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- Danger, AI Scientist, Danger - by Zvi Mowshowitzthezvi.substack.com
- Machine Studying | Jacob Xiaochen Lijacobxli.com
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
- Lapis Labslapis.rocks
- AI on Trial: Legal Models Hallucinate in 1 out of 6 (or More) Benchmarking Queries | Stanford HAIhai.stanford.edu