{"total":32,"rows":[{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"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":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"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":"2212.00196","title":"Data-Efficient Finetuning Using Cross-Task Nearest Neighbors","created":"2022-12-01","cited_by_count":26,"area":null},{"id":"2212.06803","title":"Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting","created":"2022-12-13","cited_by_count":26,"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":"2403.17691","title":"Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes","created":"2024-03-26","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":"2502.11411","title":"Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation","created":"2025-02-17","cited_by_count":9,"area":null},{"id":"2410.01285","title":"Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","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":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","cited_by_count":5,"area":null},{"id":"2507.07186","title":"Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2507.09424","title":"DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models","created":"2025-07-12","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":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2205.13022","title":"Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora","created":"2022-05-25","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":"2305.01384","title":"Class based Influence Functions for Error Detection","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2409.08958","title":"PINNfluence: Interpreting PINNs through Influence Functions","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2603.09654","title":"Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2504.13586","title":"How to Achieve Higher Accuracy with Less Training Points?","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2509.23964","title":"Detecting and Rectifying Noisy Labels: A Similarity-based Approach","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2609.31214","title":"Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}