Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings
Feb 1, 2026·
,,·
1 min read
Kartik Sharma
Yiqiao Jin
Rakshit Trivedi
Srijan Kumar
Abstract
Probing what a large language model knows is essential for safe deployment, but exhaustive probing is prohibitively expensive. We propose an efficient knowledge probing approach that adapts pre-trained embeddings to query LLM knowledge with substantially reduced compute, while preserving the fidelity of standard probing protocols.
Type
Publication
Under Review at AAAI 2026 (Preprint)
Abstract
Probing what a large language model knows is essential for safe deployment, but exhaustive probing is prohibitively expensive. We propose an efficient knowledge probing approach that adapts pre-trained embeddings to query LLM knowledge with substantially reduced compute, while preserving the fidelity of standard probing protocols.
