conftrace_

explanation fidelity

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

feature attribution (3) post-hoc explanation (2) local explainability (1) kernel shap (1) stochastic neighbor selection (1) model-agnostic explanation (1) variable-length input (1) path integration (1) explanation stability (1) psychometric testing (1)

Papers

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration AAAI 2026 ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques AAAI 2025 Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection AAAI 2024 Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training ACL 2023 Regularizing Black-box Models for Improved Interpretability NeurIPS 2020 Sanity Checks for Saliency Metrics AAAI 2020