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

2026-08-30

AI Summary

为解决文档所有者无法控制或检查生成模型的问题，SemTrace通过基于源文档事实命题的二进制签名来检测生成文本是否受到受保护文档的影响。

Abstract

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 invisibly carries a content contract that selects one fact from each binary pair and asks an instruction-following reviewer to express those facts in fixed review slots without changing its independent evaluation. A frozen natural language inference model then decodes the resulting semantic evidence with explicit erasures and scores the recovered bits against the codeword assigned to that copy. This design targets model-agnostic, assigned-copy exposure detection while keeping the watermark semantically tied to the source document.

Problem

• large language models
• provenance problem
• protected documents
• semantic watermark
• exposure detection

Innovation

• source-grounded semantic watermark
• document-specific binary signature
• natural language inference model
• model-agnostic exposure detection