{"total":120,"rows":[{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2108.11577","title":"Machine Unlearning of Features and Labels","created":"2021-08-26","cited_by_count":229,"area":"safety"},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132,"area":null},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123,"area":"diffusion"},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"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":"2106.03922","title":"Interactive Label Cleaning with Example-based Explanations","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45,"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":"2201.10055","title":"Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation","created":"2022-01-25","cited_by_count":32,"area":null},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32,"area":null},{"id":"2305.16971","title":"Theoretical and Practical Perspectives on what Influence Functions Do","created":"2023-05-26","cited_by_count":29,"area":null},{"id":"2202.12451","title":"Human-Centered Concept Explanations for Neural Networks","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2210.01072","title":"Understanding Influence Functions and Datamodels via Harmonic Analysis","created":"2022-10-03","cited_by_count":23,"area":null},{"id":"2405.15476","title":"Editable Concept Bottleneck Models","created":"2024-05-24","cited_by_count":23,"area":null},{"id":"2406.09408","title":"Data Attribution for Text-to-Image Models by Unlearning Synthesized Images","created":"2024-06-13","cited_by_count":22,"area":"safety"},{"id":"2203.12171","title":"An Empirical Study of Memorization in NLP","created":"2022-03-23","cited_by_count":21,"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":"2304.10177","title":"Regularizing Second-Order Influences for Continual Learning","created":"2023-04-20","cited_by_count":21,"area":null},{"id":"2602.05400","title":"OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration","created":"2026-02-05","cited_by_count":21,"area":null},{"id":"2303.12922","title":"Revisiting the Fragility of Influence Functions","created":"2023-03-22","cited_by_count":20,"area":null},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20,"area":null},{"id":"2409.19998","title":"Do Influence Functions Work on Large Language Models?","created":"2024-09-30","cited_by_count":20,"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":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18,"area":"safety"},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2305.13286","title":"How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning","created":"2023-05-22","cited_by_count":14,"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":"2311.08273","title":"Examining Modularity in Multilingual LMs via Language-Specialized Subnetworks","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2201.05759","title":"FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes","created":"2022-01-15","cited_by_count":12,"area":null},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2305.19765","title":"A Bayesian Approach To Analysing Training Data Attribution In Deep Learning","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2310.08782","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","created":"2023-10-13","cited_by_count":11,"area":null},{"id":"2501.05790","title":"Understanding Impact of Human Feedback via Influence Functions","created":"2025-01-10","cited_by_count":11,"area":"alignment"},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2402.03994","title":"Efficient Sketches for Training Data Attribution and Studying the Loss Landscape","created":"2024-02-06","cited_by_count":10,"area":null},{"id":"2405.12744","title":"The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning","created":"2024-05-21","cited_by_count":10,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2208.09500","title":"Causality-Inspired Taxonomy for Explainable Artificial Intelligence","created":"2022-08-19","cited_by_count":9,"area":null},{"id":"2210.14177","title":"Influence Functions for Sequence Tagging Models","created":"2022-10-25","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2408.03560","title":"In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2312.05586","title":"Deeper Understanding of Black-box Predictions via Generalized Influence Functions","created":"2023-12-09","cited_by_count":7,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2503.01052","title":"ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2511.10721","title":"Fast Data Attribution for Text-to-Image Models","created":"2025-11-13","cited_by_count":7,"area":"diffusion"},{"id":"2307.03363","title":"Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation","created":"2023-07-07","cited_by_count":6,"area":"safety"},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2410.09940","title":"Generalized Group Data Attribution","created":"2024-10-13","cited_by_count":6,"area":null},{"id":"2202.08099","title":"Measuring Unintended Memorisation of Unique Private Features in Neural Networks","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2402.11469","title":"A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models","created":"2024-02-18","cited_by_count":5,"area":null},{"id":"2405.17293","title":"Efficient Ensembles Improve Training Data Attribution","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2412.01335","title":"A Versatile Influence Function for Data Attribution with Non-Decomposable Loss","created":"2024-12-02","cited_by_count":5,"area":null},{"id":"2412.03906","title":"Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2505.19097","title":"Towards Robust Influence Functions with Flat Validation Minima","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2601.10645","title":"Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2210.13281","title":"Analyzing the Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation","created":"2022-10-24","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":"2404.14006","title":"Distilled Datamodel with Reverse Gradient Matching","created":"2024-04-22","cited_by_count":3,"area":null},{"id":"2405.10992","title":"Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System","created":"2024-05-16","cited_by_count":3,"area":null},{"id":"2501.01473","title":"Unraveling Indirect In-Context Learning Using Influence Functions","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2506.04694","title":"Influence Functions for Edge Edits in Non-Convex Graph Neural Networks","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.08169","title":"The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2409.05208","title":"Influence-based Attributions can be Manipulated","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2506.05281","title":"Fast-DataShapley: Neural Modeling for Training Data Valuation","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2507.06931","title":"DICE: Data Influence Cascade in Decentralized Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2601.00451","title":"Controllable Concept Bottleneck Models","created":"2026-01-01","cited_by_count":2,"area":null},{"id":"2106.13382","title":"A Source-Criticism Debiasing Method for GloVe Embeddings","created":"2021-06-25","cited_by_count":1,"area":null},{"id":"2205.10079","title":"Unintended memorisation of unique features in neural networks","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2305.20002","title":"Representer Point Selection for Explaining Regularized High-dimensional Models","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2402.14702","title":"InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2405.14629","title":"Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences","created":"2024-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2406.00955","title":"How Video Meetings Change Your Expression","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2406.11010","title":"WeShap: Weak Supervision Source Evaluation with Shapley Values","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2408.01365","title":"Data Debugging is NP-hard for Classifiers Trained with SGD","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2410.11540","title":"Data Quality Control in Federated Instruction-tuning of Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2412.04158","title":"LossVal: Efficient Data Valuation for Neural Networks","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2502.01669","title":"Delayed Feedback Modeling with Influence Functions","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2503.16444","title":"Conversational Explanations: Discussing Explainable AI with Non-AI Experts","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2505.23223","title":"Daunce: Data Attribution through Uncertainty Estimation","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2508.07297","title":"Revisiting Data Attribution for Influence Functions","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2509.23092","title":"Sensitivity Analysis for Diffusion Models","created":"2025-09-27","cited_by_count":1,"area":"diffusion"},{"id":"2512.12572","title":"On the Accuracy of Newton Step and Influence Function Data Attributions","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2602.10449","title":"A Unified Theory of Random Projection for Influence Functions","created":"2026-02-11","cited_by_count":1,"area":null}],"next_cursor":"100"}