The paper claims that mechanistic interpretability needs philosophy as a partner to clarify concepts, refine methods, and navigate epistemic and ethical complexities in AI systems.
Necessity and sufficiency for explaining text classifiers: A case study in hate speech detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mechanistic Interpretability Needs Philosophy
The paper claims that mechanistic interpretability needs philosophy as a partner to clarify concepts, refine methods, and navigate epistemic and ethical complexities in AI systems.