Samuel Bowman

This review discusses the current frontier of mechanistic interpretability, which aims to understand the computational mechanisms underlying neural networks. While the field has made progress, many open problems remain, including the need for improved methods, better applications to specific goals, and engagement with socio-technical challenges.

We present 11 instances of inverse scaling: tasks where language models get worse with scale rather than better, selected from 99 submissions in an open competition, the Inverse Scaling Prize.

We introduce Imitation Learning from Language Feedback (ILF) to improve code generation, demonstrating that a small amount of natural language feedback during training can lead to significant performance gains on program synthesis benchmarks.

We find that conditional training of large models (LMs), which learns the distribution over tokens based on human preference scores, reduces undesirable content while maintaining downstream task performance. Pre-training LMs with human feedback leads to better preference satisfaction than traditional LM pre-training followed by feedback-based finetuning.