SAME: Semantic Watermark Embedding for Open-Source Large Pretrained Models
cs.LG
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/sahil280114/codealpaca
Terminology
Sources
- De-mark: Watermark Removal in Large Language Models
- Provably Robust Watermarks for Open-Source Language Models
- Towards Watermarking of Open-Source LLMs
- The Llama 3 Herd of Models
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- Robust Distortion-free Watermarks for Language Models
- BadEdit: Backdooring large language models by model editing
- Scalable Fingerprinting of Large Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
- Qwen3 Technical Report
- BERTScore: Evaluating Text Generation with BERT
- Provable Robust Watermarking for AI-Generated Text
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis