{"total":24,"rows":[{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"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":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"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":"2410.17413","title":"Scalable Influence and Fact Tracing for Large Language Model Pretraining","created":"2024-10-22","cited_by_count":42,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41,"area":null},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"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":"2205.11482","title":"Towards Tracing Factual Knowledge in Language Models Back to the Training Data","created":"2022-05-23","cited_by_count":21,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2402.11750","title":"In-Context Learning Demonstration Selection via Influence Analysis","created":"2024-02-19","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":"2210.14177","title":"Influence Functions for Sequence Tagging Models","created":"2022-10-25","cited_by_count":9,"area":null},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","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":"2411.00360","title":"A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2205.11551","title":"Learning to Ignore Adversarial Attacks","created":"2022-05-23","cited_by_count":2,"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":"2504.09026","title":"Detecting Instruction Fine-tuning Attacks using Influence Function","created":"2025-04-12","cited_by_count":2,"area":null},{"id":"2508.21083","title":"CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2605.06368","title":"eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}