Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models

LCF: Linguistically-grounded code-mixing fingerprints for LLM ownership verification

A new arXiv preprint introduces LCF (Linguistically-Constructed Fingerprints), a unified framework for embedding ownership signals into LLMs via code-mixed triggers that combine low-resource languages under semantic-density substitution and grammar-biased mixing rules. The companion injection method, LCFEdit, uses null-space projection from multilingual representations to embed fingerprints while preserving model utility. The approach addresses two known weaknesses of prior fingerprinting methods: accidental activation of natural-language triggers and perplexity-based filtering of garbled triggers. Evaluations report persistent ownership verification with negligible utility degradation.