{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"1901.09392","title":"On the (In)fidelity and Sensitivity for Explanations","created":"2019-01-27","cited_by_count":310},{"id":"1706.03691","title":"Certified Defenses for Data Poisoning Attacks","created":"2017-06-09","cited_by_count":303},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2005.00631","title":"Evaluating and Aggregating Feature-based Model Explanations","created":"2020-05-01","cited_by_count":188},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"2012.15781","title":"FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging","created":"2020-12-31","cited_by_count":120},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91},{"id":"1306.4265","title":"Bounding the Estimation Error of Sampling-based Shapley Value Approximation","created":"2013-06-18","cited_by_count":58},{"id":"2004.02015","title":"Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection","created":"2020-04-04","cited_by_count":57},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2104.04128","title":"An Empirical Comparison of Instance Attribution Methods for NLP","created":"2021-04-09","cited_by_count":35},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34},{"id":"2302.00736","title":"Approximating the Shapley Value without Marginal Contributions","created":"2023-02-01","cited_by_count":34},{"id":"2404.07662","title":"PINNACLE: PINN Adaptive ColLocation and Experimental points selection","created":"2024-04-11","cited_by_count":32},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22},{"id":"2306.10165","title":"Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values","created":"2023-06-16","cited_by_count":21},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13},{"id":"2310.00646","title":"Source Attribution for Large Language Model-Generated Data","created":"2023-10-01","cited_by_count":11},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10},{"id":"2306.05764","title":"Fair yet Asymptotically Equal Collaborative Learning","created":"2023-06-09","cited_by_count":8},{"id":"2401.14846","title":"Understanding Domain Generalization: A Noise Robustness Perspective","created":"2024-01-26","cited_by_count":8},{"id":"2106.05484","title":"A Unified Framework for Task-Driven Data Quality Management","created":"2021-06-10","cited_by_count":7},{"id":"2106.13346","title":"What will it take to generate fairness-preserving explanations?","created":"2021-06-24","cited_by_count":7},{"id":"2306.04454","title":"Training-Free Neural Active Learning with Initialization-Robustness Guarantees","created":"2023-06-07","cited_by_count":5},{"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}],"next_cursor":null}