GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
cs.LG, cs.AI, cs.CL
Submitted: 2025-06-12
Updated: 2026-10-13
Terminology
Sources
- Matching-Theory-Based Multi-User Cooperative Computing Framework
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
- A Topological Data Analysis of the CHIME/FRB Catalogues
- Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
- Constraints on Sub-GeV Dark Matter--Electron Scattering from the CDEX-10 Experiment
- UNCOVERing the contribution of black holes to reionization in the JWST era
- WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- Textbooks Are All You Need II: phi-1.5 technical report
- Counting Molecules: Python based scheme for automated enumeration and categorization of molecules in scanning tunneling microscopy images
- Distributionally Robust Receive Combining
- TOFU: A Task of Fictitious Unlearning for LLMs
- Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
- DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform
- Training language models to follow instructions with human feedback
- Nonlinear electrodynamics for the vacuum of Dirac materials. Photon magnetic properties and radiation pressures
- A scalable estimate of the extra-sample prediction error via approximate leave-one-out
- MUSE: Machine Unlearning Six-Way Evaluation for Language Models
- Double-well Net for Image Segmentation
- LLaMA: Open and Efficient Foundation Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks