Search Results for author:
Found 3 papers, 2 papers with code
Approaching Human-Level Forecasting with Language Models
In this work, we study whether language models (LMs) can forecast at the level of competitive human forecasters.
Overthinking the Truth: Understanding how Language Models Process False Demonstrations
The first phenomenon, overthinking, appears when we decode predictions from intermediate layers, given correct vs. incorrect few-shot demonstrations.
Eliciting Latent Predictions from Transformers with the Tuned Lens
We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
