{"total":123,"rows":[{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98,"area":null},{"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":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2410.13850","title":"Influence Functions for Scalable Data Attribution in Diffusion Models","created":"2024-10-17","cited_by_count":33,"area":"diffusion"},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","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":"2410.18639","title":"Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models","created":"2024-10-24","cited_by_count":22,"area":"diffusion"},{"id":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22,"area":"safety"},{"id":"2311.09763","title":"Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations","created":"2023-11-16","cited_by_count":21,"area":"safety"},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"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":"2404.16621","title":"Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare","created":"2024-04-25","cited_by_count":15,"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":"2505.07437","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"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":"2501.05790","title":"Understanding Impact of Human Feedback via Influence Functions","created":"2025-01-10","cited_by_count":11,"area":"alignment"},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2405.03869","title":"Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2405.20456","title":"Scaling Laws for the Value of Individual Data Points in Machine Learning","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2602.17835","title":"Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning","created":"2026-02-19","cited_by_count":10,"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":"2404.18870","title":"More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness","created":"2024-04-29","cited_by_count":9,"area":"alignment"},{"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":"2502.00198","title":"Fairshare Data Pricing via Data Valuation for Large Language Models","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2505.18976","title":"GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection","created":"2025-05-25","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":"2504.18524","title":"Augmenting Perceptual Super-Resolution via Image Quality Predictors","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2407.15247","title":"TimeInf: Time Series Data Contribution via Influence Functions","created":"2024-07-21","cited_by_count":6,"area":null},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2404.01361","title":"LLM Attributor: Interactive Visual Attribution for LLM Generation","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2405.14899","title":"DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning","created":"2024-05-22","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":"2507.09424","title":"DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models","created":"2025-07-12","cited_by_count":5,"area":null},{"id":"2511.04715","title":"First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2512.05925","title":"To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis","created":"2025-12-05","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":"2403.04529","title":"Enhancing Data Quality in Federated Fine-Tuning of Foundation Models","created":"2024-03-07","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":"2505.19097","title":"Towards Robust Influence Functions with Flat Validation Minima","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2506.21910","title":"AutoMixer: Checkpoint Artifacts as Automatic Data Mixers","created":"2025-06-27","cited_by_count":4,"area":null},{"id":"2507.03004","title":"CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics","created":"2025-07-02","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":"2510.13212","title":"Towards Understanding Valuable Preference Data for Large Language Model Alignment","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"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":"2602.03783","title":"Efficient Estimation of Kernel Surrogate Models for Task Attribution","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2602.14696","title":"A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2404.00412","title":"CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion","created":"2024-03-30","cited_by_count":3,"area":"diffusion"},{"id":"2412.08637","title":"DMin: Scalable Training Data Influence Estimation for Diffusion Models","created":"2024-12-11","cited_by_count":3,"area":"diffusion"},{"id":"2501.01473","title":"Unraveling Indirect In-Context Learning Using Influence Functions","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2508.14648","title":"Understanding Data Influence with Differential Approximation","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2510.07118","title":"TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning","created":"2025-10-08","cited_by_count":3,"area":"alignment"},{"id":"2510.11832","title":"Z0-Inf: Zeroth Order Approximation for Data Influence","created":"2025-10-13","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":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","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":"2410.07158","title":"Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2410.20019","title":"Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions","created":"2024-10-26","cited_by_count":2,"area":"safety"},{"id":"2502.01703","title":"QLESS: A Quantized Approach for Data Valuation and Selection in Large Language Model Fine-Tuning","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2504.06219","title":"Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2507.14344","title":"Influence Functions for Preference Dataset Pruning","created":"2025-07-18","cited_by_count":2,"area":"alignment"},{"id":"2509.15651","title":"Toward Efficient Influence Function: Dropout as a Compression Tool","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","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":"2512.06678","title":"GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning","created":"2025-12-07","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":"2605.15675","title":"Interaction-Aware Influence Functions for Group Attribution","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.21489","title":"Variance Reduction for Expectations with Diffusion Teachers","created":"2026-05-20","cited_by_count":2,"area":"diffusion"},{"id":"2605.30337","title":"Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2407.14859","title":"Enhancing High-Energy Particle Physics Collision Analysis through Graph Data Attribution Techniques","created":"2024-07-20","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":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","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":"2602.02891","title":"TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation","created":"2026-02-02","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},{"id":"2603.00342","title":"Challenges in Enabling Private Data Valuation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.09056","title":"Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning","created":"2026-03-10","cited_by_count":1,"area":"offlinerl"},{"id":"2603.29466","title":"An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.21422","title":"PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.05165","title":"STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.18307","title":"DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.25488","title":"Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning","created":"2026-06-24","cited_by_count":1,"area":"distill"},{"id":"2606.26036","title":"Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2607.00641","title":"What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.11347","title":"Do Neural Networks Preserve Case Structure? Case-Based Decomposition, Interpretation, and Decision Consistency","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.11898","title":"TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2608.19762","title":"Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2403.08812","title":"Gore Diffusion LoRA Model","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2406.14207","title":"LayerMatch: Do Pseudo-labels Benefit All Layers?","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2408.06257","title":"Reciprocal Learning","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2506.00002","title":"Advancing AI-assisted Hardware Design with Hierarchical Decentralized Training and Personalized Inference-Time Optimization","created":"2025-04-21","cited_by_count":0,"area":null}],"next_cursor":"100"}