{"total":34,"rows":[{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2109.00544","title":"Towards Improving Adversarial Training of NLP Models","created":"2021-09-01","cited_by_count":79,"area":null},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2104.04488","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2203.12709","title":"Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation","created":"2022-03-23","cited_by_count":12,"area":null},{"id":"2210.11528","title":"Unsupervised Text Deidentification","created":"2022-10-20","cited_by_count":11,"area":null},{"id":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2207.04447","title":"Human-Centric Research for NLP: Towards a Definition and Guiding Questions","created":"2022-07-10","cited_by_count":9,"area":null},{"id":"2403.07955","title":"Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2106.06528","title":"Local Explanation of Dialogue Response Generation","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2112.05364","title":"Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2209.10951","title":"An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning","created":"2022-09-22","cited_by_count":6,"area":null},{"id":"2302.02016","title":"Improving Interpretability via Explicit Word Interaction Graph Layer","created":"2023-02-03","cited_by_count":6,"area":null},{"id":"2405.20404","title":"JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2202.09792","title":"Hierarchical Interpretation of Neural Text Classification","created":"2022-02-20","cited_by_count":5,"area":null},{"id":"2404.03098","title":"Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2303.02860","title":"A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification","created":"2023-03-06","cited_by_count":4,"area":null},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2204.08039","title":"Pathologies of Pre-trained Language Models in Few-shot Fine-tuning","created":"2022-04-17","cited_by_count":3,"area":null},{"id":"2305.09400","title":"Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2212.05327","title":"Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2302.10479","title":"Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2501.16374","title":"SAFR: Neuron Redistribution for Interpretability","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2506.07446","title":"Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2203.14474","title":"Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking","created":"2022-03-28","cited_by_count":1,"area":null},{"id":"2402.18145","title":"Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2308.16584","title":"Unsupervised Text Style Transfer with Deep Generative Models","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2312.08157","title":"CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2404.02068","title":"Using Interpretation Methods for Model Enhancement","created":"2024-04-02","cited_by_count":0,"area":null}],"next_cursor":null}