{"total":37,"rows":[{"id":"2509.26544","title":"Bayesian Influence Functions for Hessian-Free Data Attribution","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"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":"2601.10645","title":"Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2602.14696","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":"2604.01597","title":"Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2506.05647","title":"Learning to Weight Parameters for Training Data Attribution","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2508.11017","title":"Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2601.21929","title":"LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2606.11660","title":"Bergson: An Open Source Library for Data Attribution","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","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":"2505.12621","title":"SAFE: Improving LLM Systems using Sentence-Level In-generation Attribution","created":"2025-05-19","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":"2507.01844","title":"Low-Perplexity LLM-Generated Sequences and Where To Find Them","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2604.16197","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","created":"2026-04-17","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":"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":"2608.13515","title":"Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2609.19589","title":"Form Over Content In Gradient-Based Data Attribution Methods","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2609.37914","title":"The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2509.12581","title":"Exploring Training Data Attribution under Limited Access Constraints","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.14261","title":"Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.27313","title":"LLM generation novelty through the lens of semantic similarity","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2603.27094","title":"Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2606.04928","title":"Data Attribution in Large Language Models via Bidirectional Gradient Optimization","created":"2026-06-03","cited_by_count":0,"area":null},{"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":"2606.23591","title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.24890","title":"Small edits, large models: How Wikipedia advocacy shapes LLM values","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2607.10020","title":"FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora","created":"2026-07-10","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":"2609.33667","title":"Scalable Attribution and Control of Model Behavior During Training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37842","title":"Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection","created":"2026-09-29","cited_by_count":0,"area":null},{"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":"2610.03432","title":"OptiSelect: How does the Optimizer Shape Data Curriculum?","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}