Fixed counterfactual explanation datasets train LMs such that generated explanations track the model's evolving behavior rather than the fixed targets, due to persistent correlation during training.
Do natural language descriptions of model activations convey privileged information? In Mechanistic Interpretability Workshop at NeurIPS 2025, 2025 b
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
Fixed counterfactual explanation datasets train LMs such that generated explanations track the model's evolving behavior rather than the fixed targets, due to persistent correlation during training.