influence function

On the Feasibility of In-Context Probing for Data Attribution NAACL 2025 Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models ICML 2025 Regularizing Energy among Training Samples for Out-of-Distribution Generalization ICLR 2025 RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity NAACL 2025 ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning EMNLP 2025 RRInf: Efficient Influence Function Estimation via Ridge Regression for Large Language Models and Text-to-Image Diffusion Models EMNLP 2025 Scalable Influence and Fact Tracing for Large Language Model Pretraining ICLR 2025 Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization IJCAI 2025 Semiparametric conformal prediction AISTATS 2025 TimeInf: Time Series Data Contribution via Influence Functions ICLR 2025 Towards Robust Influence Functions with Flat Validation Minima ICML 2025 Understanding Impact of Human Feedback via Influence Functions ACL 2025 Unified Parameter-Efficient Unlearning for LLMs ICLR 2025 Unraveling the Influence of Training Data and Internal Structures in Large Language Models for Enhanced Explainability (Student Abstract) AAAI 2025 Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation IJCAI 2025 dattri: A Library for Efficient Data Attribution NeurIPS 2024 Adaptive Instrument Design for Indirect Experiments ICLR 2024 A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective NeurIPS 2024 Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions EMNLP 2024 Category-Aware Active Domain Adaptation ICML 2024 Countering Personalized Text-to-Image Generation with Influence Watermarks CVPR 2024 Data Attribution for Text-to-Image Models by Unlearning Synthesized Images NeurIPS 2024 DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models ICLR 2024 DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning NeurIPS 2024 Distilled Datamodel with Reverse Gradient Matching CVPR 2024