PPaperPicks

Anna Hedström

6 papers at tracked venues · 5 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Benchmarking XAI Explanations with Human-Aligned Evaluations
  2. Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
  3. Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution
  4. To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
    ICML 2025 · Anna Hedström
  5. CoSy: Evaluating Textual Explanations of Neurons
  6. From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation