Embedding-Space Fingerprinting of LoRA Fine-Tunes: Recovering the Training-Data Domain from the Model Artifact Alone
cs.AI, cs.CL, cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Can We Infer Confidential Properties of Training Data from LLMs?
- Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
- Natural Fingerprints of Large Language Models
- Predicting Neural Network Accuracy from Weights
- Delta Activations: A Representation for Finetuned Large Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents