no code implementations • 28 Feb 2024 • Danny Halawi, Fred Zhang, Chen Yueh-Han, Jacob Steinhardt
In this work, we study whether language models (LMs) can forecast at the level of competitive human forecasters.
1 code implementation • 18 Jul 2023 • Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt
The first phenomenon, overthinking, appears when we decode predictions from intermediate layers, given correct vs. incorrect few-shot demonstrations.
2 code implementations • 14 Mar 2023 • Nora Belrose, Zach Furman, Logan Smith, Danny Halawi, Igor Ostrovsky, Lev McKinney, Stella Biderman, Jacob Steinhardt
We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer.