arXiv (All)
open access
Perturbation, Not Provenance: Why Activation Steering Does Not Make a Robust Text Watermark
Linear directions in the activation space of large language models causally and universally influence model behavior. This suggests that they might serve as a basis for a robust text watermark. The idea is to steer the generation along a specific semantic direction and then recover the mark by probi
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding#1061671
- Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings#324824
- WoE Wrote It? Watermarking Mixture-of-Experts LLMs for Black-Box Text Provenance#793972
- WoE Wrote It? Watermarking Mixture-of-Experts LLMs for Black-Box Text Provenance#789953
- Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG#1356654
Record · ID 1343017
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive