{"total":81,"rows":[{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2412.09538","title":"Capturing the Temporal Dependence of Training Data Influence","created":"2024-12-12","cited_by_count":35,"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":"2506.11849","title":"Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values","created":"2025-06-13","cited_by_count":19,"area":null},{"id":"2505.17895","title":"DataRater: Meta-Learned Dataset Curation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"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":"2502.00198","title":"Fairshare Data Pricing via Data Valuation for Large Language Models","created":"2025-01-31","cited_by_count":8,"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":"2601.17858","title":"MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging","created":"2026-01-25","cited_by_count":7,"area":null},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2501.06261","title":"CAMs as Shapley Value-based Explainers","created":"2025-01-09","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":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2410.00759","title":"Targeted synthetic data generation for tabular data via hardness characterization","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2505.24261","title":"Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2510.04787","title":"Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2605.18814","title":"How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2507.06547","title":"Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution","created":"2025-07-09","cited_by_count":3,"area":"diffusion"},{"id":"2510.11832","title":"Z0-Inf: Zeroth Order Approximation for Data Influence","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2512.05958","title":"MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2601.09966","title":"A Sustainable AI Economy Needs Data Deals That Work for Generators","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2601.19040","title":"OATS: Online Data Augmentation for Time Series Foundation Models","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2602.00329","title":"In-Run Data Shapley for Adam Optimizer","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2603.17945","title":"ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2504.05563","title":"Do Data Valuations Make Good Data Prices?","created":"2025-04-07","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":"2507.11895","title":"Newfluence: Boosting Model interpretability and Understanding in High Dimensions","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2510.16007","title":"Layer-Aware Influence for Online Data Valuation Estimation","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2602.01312","title":"Imperfect Influence, Preserved Rankings: A Theory of TRAK for Data Attribution","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2603.09865","title":"GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2605.06920","title":"In-Context Credit Assignment via the Core","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2412.04158","title":"LossVal: Efficient Data Valuation for Neural Networks","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2502.04554","title":"Unifying and Optimizing Data Values for Selection via Sequential Decision-Making","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2506.23799","title":"KAIROS: Scalable Model-Agnostic Data Valuation","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2508.10180","title":"For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs","created":"2025-08-13","cited_by_count":1,"area":"mllm"},{"id":"2511.16087","title":"AssayMatch: Learning to Select Data for Molecular Activity Models","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.15765","title":"Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization","created":"2025-12-12","cited_by_count":1,"area":"alignment"},{"id":"2603.00342","title":"Challenges in Enabling Private Data Valuation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.03672","title":"Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.29871","title":"ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.00001","title":"Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2606.01635","title":"AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2608.13515","title":"Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2610.10426","title":"CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution","created":"2026-10-07","cited_by_count":1,"area":null},{"id":"2508.16255","title":"Chunked Data Shapley: A Scalable Dataset Quality Assessment for Machine Learning","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2509.07909","title":"Uncovering Scaling Laws for Large Language Models via Inverse Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.03950","title":"What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2510.10510","title":"f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.10902","title":"Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2511.02100","title":"Geometric Data Valuation via Leverage Scores","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2511.06463","title":"Error Estimate and Convergence Analysis for Data Valuation","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2511.07975","title":"Reliable and Private Utility Signaling for Data Markets","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2511.14197","title":"Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision","created":"2025-11-18","cited_by_count":0,"area":"distill"},{"id":"2601.16651","title":"Select or Project? Evaluating Lower-dimensional Vectors for LLM Training Data Explanations","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2601.22016","title":"TBDFiltering: Sample-Efficient Tree-Based Data Filtering","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2601.22276","title":"SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models","created":"2026-01-29","cited_by_count":0,"area":"diffusion"},{"id":"2604.04892","title":"Data Attribution in Adaptive Learning","created":"2026-04-06","cited_by_count":0,"area":"deeprl"},{"id":"2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.15520","title":"On the Fragility of Data Attribution When Learning Is Distributed","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.15877","title":"Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.20620","title":"Dynamic Shapley Computation","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.21033","title":"Efficient Banzhaf-Based Data Valuation for $k$-Nearest Neighbors Classification","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.30919","title":"De-attribute to Forget for LLM Unlearning","created":"2026-05-29","cited_by_count":0,"area":"safety"},{"id":"2606.06892","title":"GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.03346","title":"Efficient Decentralized Multi-task Dataset Valuation via Model Merging","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.22522","title":"From Detrimental to Beneficial: Dynamic Influence-based Valuation and Editing","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.19985","title":"Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.32380","title":"Traceprop: Training Data Attribution in a Single Pass","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32484","title":"Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33667","title":"Scalable Attribution and Control of Model Behavior During Training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35072","title":"Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.38767","title":"dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00436","title":"Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03432","title":"OptiSelect: How does the Optimizer Shape Data Curriculum?","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04310","title":"Modeling Deletion Requests in Machine Unlearning","created":"2026-10-03","cited_by_count":0,"area":"safety"},{"id":"2610.06542","title":"A Fine-Grained Analysis of the LoRA Fine-Tuning Landscape with Implications for Data Selection","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.19343","title":"Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}