Anna Hedström

6 papers · 2022–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🔥 Unstoppable · Bronze ❓ The Questioner

Venues

AAAI (3) ICML (1) JMLR (1) NeurIPS (1)

Top co-authors

Marina M.-C. Höhne (4) Sebastian Lapuschkin (2) Kirill Bykov (2) Nicolas Bousquet (1) Tom Bewley (1) Manuela Veloso (1) Carlos Eiras-Franco (1) Philine Lou Bommer (1) David Filliat (1) Patricia Delhomme (1)

Research topics

Artificial Intelligence (6) Core AI (6) Machine Learning (3) Deep Learning (2) Core Methods (2) Learning Types · Deep Learning (2) Techniques (2) Natural Language Processing (1) Learning Types · Machine Learning (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

neural network (2) explainable ai (2) model explanation (2) weight perturbation (1) concept learning (1) abstention (1) generative model (1) latent representation (1) deep neural network (1) local explanation (1) language model (1) decision boundary (1) neuron explanation (1) concept synthesis (1) textual description (1) concept discovery (1) black-box model (1) stochastic perturbation (1) distribution estimation (1) explainable artificial intelligence (1)

Papers

Benchmarking XAI Explanations with Human-Aligned Evaluations AAAI 2026 Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution AAAI 2025 To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models ICML 2025 CoSy: Evaluating Textual Explanations of Neurons NeurIPS 2024 Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond JMLR 2023 NoiseGrad — Enhancing Explanations by Introducing Stochasticity to Model Weights AAAI 2022