Privacy-preserving language model watermarks with aggregate estimation
Red-Green Sequence watermarks enable accurate population-level frequency estimation while limiting individual privacy leakage.
40
AI model
language models
- Mentions · 7d0
- Mentions · 30d2
- All mentions2
- First seenNov 3, 2026
- Last mentioned7d ago
Timeline
2 articles · newest firstStateBench tests language models on state changes in long documents
Benchmark evaluates how language models track state changes over extended documents.
30
Appears with
- statebenchproduct · 1
- huggingfacevendor · 1
- allenaiorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.