conftrace_

faithfulness metric

13 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model explanation (3) feature attribution (3) large language model (2) language model (2) benchmark dataset (2) model interpretability (2) text generation (2) natural language processing (2) description evaluation (1) free-text explanation (1)

Papers

A Causal Lens for Evaluating Faithfulness Metrics EMNLP 2025 FADE: Why Bad Descriptions Happen to Good Features ACL 2025 LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions CVPR 2025 Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attributions Explainability ACL 2025 Towards Attributions of Input Variables in a Coalition ICML 2025 Pre-trained Language Models Return Distinguishable Probability Distributions to Unfaithfully Hallucinated Texts EMNLP 2024 The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models ACL 2024 VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models ACL 2024 A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization MLHC 2023 BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics ACL 2023 Incorporating Attribution Importance for Improving Faithfulness Metrics ACL 2023 A Comparative Study of Faithfulness Metrics for Model Interpretability Methods ACL 2022 How (Un)Faithful is Attention? EMNLP 2022