conftrace_

faithfulness test

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

layer-wise relevance propagation (1) instance attribution (1) neuron attribution (1) test-time reasoning (1) training instance (1) attention gradient (1) choices-only input (1) parametric knowledge (1) model explainability (1) counterfactual evaluation (1)

Papers

Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers ACL 2026 Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods ACL 2024 Faithfulness Tests for Natural Language Explanations ACL 2023 Rethinking Attention-Model Explainability through Faithfulness Violation Test ICML 2022