Law
Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
Gaussian mechanism borrowed from differential privacy.
End-to-End Ontology Learning with Large Language Models
Ontologies are useful for automatic machine processing of domain knowledge as they represent it in a structured format.
WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games
Recently, large language models (LLMs) have achieved superior performance, empowering the development of large multimodal agents (LMAs).
Stability Guarantees for Feature Attributions with Multiplicative Smoothing
In this work, we analyze stability as a property for reliable feature attribution methods.
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data.
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making
Most of the literature in fair machine learning focuses on defining and achieving fairness criteria in the context of prediction, while not explicitly focusing on how these predictions may be used later on in the pipeline.
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
Ideally, we would like methods that train LMs only once ( i.e., one-shot) with a fixed objective, as in
