{"total":36,"rows":[{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2303.08114","title":"Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs","created":"2023-03-14","cited_by_count":53,"area":null},{"id":"2305.13299","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","created":"2023-05-22","cited_by_count":49,"area":null},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2205.12600","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","cited_by_count":25,"area":null},{"id":"2205.12640","title":"Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing","created":"2022-05-25","cited_by_count":16,"area":null},{"id":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","cited_by_count":15,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2302.02169","title":"How Many and Which Training Points Would Need to be Removed to Flip this Prediction?","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2210.14177","title":"Influence Functions for Sequence Tagging Models","created":"2022-10-25","cited_by_count":9,"area":null},{"id":"2404.18655","title":"Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods","created":"2024-04-29","cited_by_count":9,"area":null},{"id":"2305.16863","title":"Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","cited_by_count":5,"area":null},{"id":"2511.04715","title":"First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2210.13439","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2310.11303","title":"QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering","created":"2023-10-17","cited_by_count":4,"area":null},{"id":"2305.12809","title":"Relabeling Minimal Training Subset to Flip a Prediction","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2310.20477","title":"Exploring Practitioner Perspectives On Training Data Attribution Explanations","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2406.13724","title":"Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2409.16978","title":"Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2211.05485","title":"Understanding Text Classification Data and Models Using Aggregated Input Salience","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2312.09718","title":"Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2510.09135","title":"Training Feature Attribution for Vision Models","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2210.07126","title":"Challenges in Explanation Quality Evaluation","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","cited_by_count":0,"area":null}],"next_cursor":null}