SOURCE-LINKED INTELLIGENCE

SemTrace: Source-Grounded Semantic Signatures for Tracing LLM Exposure to Protected Documents

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Large language models are increasingly used to read documents and produce downstream text, creating a provenance problem when the document owner cannot control or inspect the model that performs the generation. We introduce SemTrace, a source-grounded semantic watermark for detecting whether a generated review was influenced by a known protected manuscript copy. Rather than biasing token probabilities or imposing surface-form patterns, SemTrace constructs a document-specific binary signature from factual propositions that are directly supported by the manuscript itself. A protected PDF invisib

Read original source ↗ Open in workspace

recordType

paper

region

Global