Gerhard Wunder
4 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(13)
Conferences
ICML (2)
AAAI (1)
EMNLP (1)
Top co-authors
Keywords
factual accuracy
(1)
feature attribution
(1)
distribution shift
(1)
latent feature discovery
(1)
sparse projection
(1)
mechanistic interpretability
(1)
hallucination detection
(1)
model decision
(1)
latent feature
(1)
explanation evaluation
(1)
model steering
(1)
latent direction
(1)
input manipulation
(1)
Papers
Rethinking Explanation Evaluation Under the Retraining Scheme
AAAI 2026
Where Confabulation Lives: Latent Feature Discovery in LLMs
EMNLP 2025
GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation
ICML 2025
On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
ICML 2024