Conceptio
›
Archive
›
arXiv (All)
arXiv (All)
open access
Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities
Le, Linh et al.
arXiv (All) · Papers · License: Open Access
Open Source ↗
Direct PDF ↓
machine learning, artificial intelligence
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Related documents
GLaMoR: Consistency Checking of OWL Ontologies using Graph Language Models
#1000502
TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
#1000497
A Generalized Tangent Approximation based Variational Inference Framework for Strongly Super-Gaussian Likelihoods
#1000498
Reinforcement Learning from Human Feedback
#1000499
Towards Large Language Models for Lunar Mission Planning and In Situ Resource Utilization
#1000503
Record
· ID 794242
Retrieved via
Conceptio
— every document is proof-bundled with source, license, and retrieval metadata.