conftrace_

human-interpretable concept

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

concept-based interpretation (1) interpretable framework (1) concept-based reasoning (1) model transparency (1) causal intervention (1) concept bottleneck (1) model generalization (1) spurious correlation (1) language model (1) explanation generation (1)

Papers

Connecting Concept Layers and Rationales to Enhance Language Model Interpretability EMNLP 2025 Discover and Cure: Concept-aware Mitigation of Spurious Correlation ICML 2023