Causal inference has shown potential in enhancing the predictive accuracy, fairness,
robustness, and explainability of Natural Language Processing (NLP) models by capturing …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Obtaining human-interpretable explanations of large, general-purpose language models is
an urgent goal for AI safety. However, it is just as important that our interpretability methods …

Conversational large language models are fine-tuned for both instruction-following and
safety, resulting in models that obey benign requests but refuse harmful ones. While this …

Recent research in mechanistic interpretability has attempted to reverse-engineer
Transformer models by carefully inspecting network weights and activations. However, these …

Understanding AI systems' inner workings is critical for ensuring value alignment and safety.
This review explores mechanistic interpretability: reverse-engineering the computational …

Mechanistic interpretability seeks to understand the internal mechanisms of machine
learning models, where localization--identifying the important model components--is a key …

Natural language is an appealing medium for explaining how large language models
process and store information, but evaluating the faithfulness of such explanations is …

Parameter-efficient fine-tuning (PEFT) methods seek to adapt large models via updates to a
small number of weights. However, much prior interpretability work has shown that …

Localizing behaviors of neural networks to a subset of the network's components or a subset
of interactions between components is a natural first step towards analyzing network …