{"total":19,"rows":[{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2311.09335","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2210.09197","title":"On the Impact of Temporal Concept Drift on Model Explanations","created":"2022-10-17","cited_by_count":14,"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":"2211.03041","title":"Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates","created":"2022-11-06","cited_by_count":7,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2403.12809","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2504.02911","title":"Noiser: Bounded Input Perturbations for Attributing Large Language Models","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2203.12536","title":"Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2505.01198","title":"Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2409.17774","title":"Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2302.09190","title":"Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2306.01206","title":"Estimating Semantic Similarity between In-Domain and Out-of-Domain Samples","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2209.08681","title":"Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2305.07988","title":"Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts","created":"2023-05-13","cited_by_count":0,"area":null}],"next_cursor":null}