ServiceNow AI Research

Explainability

Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
Language model activations entangle concepts that mediate their behavior, making it difficult to interpret these factors, which has …
Understanding Stakeholders' Perceptions and Needs Across the LLM Supply Chain
Explainability and transparency of AI systems are undeniably important, leading to several research studies and tools addressing them. …
Explaining Graph Neural Networks Using Interpretable Local Surrogates
We propose an interpretable local surrogate (ILS) method for understanding the predictions of black-box graph models. Explainability …
Explainable, Sensible and Virtuous Workplace Chatbots
We outline three research directions towards the practical implementation of explainable, sensible and virtuous chatbots for the …
Explaining by Example: A Practitioner’s Perspective
Black-box machine learning (ML) models have become increasingly popular in practice. They can offer great performance, especially in …
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Explainability for machine learning models has gained considerable attention within the research community given the importance of …
RelatIF: Identifying Explanatory Training Examples via Relative Influence
In this work, we focus on the use of influence functions to identify relevant training examples that one might hope …