Lune

Profiles2020-2024

Peter Hase

UNC Chapel Hill

11Papers
0Last author
7Unique co-authors
5First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers11

  1. Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction AttacksAuthor 2 of 3ICLR 2024 · 167 citations
  2. The Unreasonable Effectiveness of Easy Training Data for Hard TasksAuthor 1 of 4ACL 2024 · 3 citations
  3. Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language ModelsAuthor 1 of 4NeurIPS 2023 · 307 citations
  4. Can Language Models Teach? Teacher Explanations Improve Student Performance via PersonalizationAuthor 2 of 3NeurIPS 2023 · 21 citations
  5. Summarization Programs: Interpretable Abstractive Summarization with Neural Modular TreesAuthor 3 of 4ICLR 2023 · 7 citations
  6. Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous ObjectsAuthor 2 of 3NeurIPS 2023 · 2 citations
  7. VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason ObjectivesAuthor 2 of 3NeurIPS 2022 · 16 citations
  8. The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance ExplanationsAuthor 1 of 3NeurIPS 2021 · 121 citations
  9. FastIF: Scalable Influence Functions for Efficient Model Interpretation and DebuggingAuthor 3 of 5EMNLP 2021 · 51 citations
  10. Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?Author 1 of 2ACL 2020 · 216 citations
  11. Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?Author 1 of 4EMNLP Findings 2020 · 62 citations
Dusk over the sea between two cliffs drawn in fine vertical lines