Paper-Conference

Understanding Addition in Transformers
DeepDecipher: Accessing and Investigating Neuron Activation in Large Language Models
Measuring Value Alignment
Detecting Edit Failures in Large Language Models: An Improved Specificity Benchmark
The Larger They Are, the Harder They Fail: Language Models Do Not Recognize Identifier Swaps in Python
Neuron to Graph: Interpreting Language Model Neurons at Scale
System III: Learning with Domain Knowledge for Safety Constraints