conftrace_

faithful explanation

37 papers

Explore in graph

Co-occurring keywords

model interpretability (519) feature attribution (280) large language model (13587) text classification (6793) explainable ai (480) natural language explanation (82) knowledge graph (1837) natural language inference (1287) attention mechanism (4001) gradient-based attribution (17)

Papers

An Empirical Study on Explanations in Out-of-Domain Settings ACL 2022
ProtoTEx: Explaining Model Decisions with Prototype Tensors ACL 2022
Locally Distributed Activation Vectors for Guided Feature Attribution COLING 2022
Faithful Knowledge Graph Explanations in Commonsense Question Answering EMNLP 2022
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience EMNLP 2021
Measuring Association Between Labels and Free-Text Rationales EMNLP 2021
Faithfully Explainable Recommendation via Neural Logic Reasoning NAACL 2021
Rationales for Sequential Predictions EMNLP 2021
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? ACL 2020
Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection ACL 2020
Towards Transparent and Explainable Attention Models ACL 2020
Learning to Faithfully Rationalize by Construction ACL 2020