Year: 2026
Type: conference-paper
Abstract: Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited.We argue that this gap stems from misaligned incentives among LLM providers, platforms, and end users, which manifest as three key barriers: competitive risk, detection-tool governance, and attribution issues.We revisit three classes of watermarking through this lens.Model watermarking naturally aligns with LLM provider interests, yet faces new challenges in open-source ecosystems.LLM text watermarking offers modest provider benefit when framed solely as an anti-misuse tool, but can gain traction in narrowly scoped settings such as dataset decontamination or user-controlled provenance.In-context watermarking (ICW) is tailored for trusted parties, such as conference organizers or educators, who embed hidden watermarking instructions into documents.If a dishonest reviewer or student submits this text to an LLM, the output carries a detectable watermark indicating misuse.This setup aligns incentives: users experience no quality loss, trusted parties gain a detection tool, and LLM providers remain neutral by simply following watermark instructions.We advocate for a broader exploration of incentive-aligned methods, with ICW as an example, in domains where trusted parties need reliable tools to detect misuse.More broadly, we distill design principles for incentive-aligned, domain-specific watermarking and outline future research directions.Our position is that the practical adoption of LLM watermarking requires aligning stakeholder incentives in targeted application domains and fostering active community engagement.
Authors: Yepeng Liu, Xuandong Zhao, Dawn Song, Gregory W. Wornell, Yuheng Bu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4416056051