Hassan Sajjad

Associate Professor@Dalhousie University·加拿大·OpenReview

研究方向

machine translation · natural language processing · interpretation and analysis of deep neural network models · generative models · NLP · explainable AI · safety alignment · model editing

7.0

合作者 (20)

Hassan Sajjad

Data-centric Prediction Explanation via Kernelized Stein Discrepancy

Explaining the role of Intrinsic Dimensionality in Adversarial Training

Dependency Parsing is More Parameter-Efficient with Normalization

Resolving Lexical Bias in Edit Scoping with Projector Editor Networks

Resolving Lexical Bias in Model Editing

Towards Understanding the Feasibility of Machine Unlearning

SMAAT: Scalable Manifold-Aware Adversarial Training for Large Language Models

Representation Noising: A Defence Mechanism Against Harmful Finetuning

Latent Concept-based Explanation of NLP Models

Gazelle: A Multimodal Learning System Robust to Missing Modalities