IBM Releases LLMON Preview Models Based on Granite 4.1 3B and 8B
Start here
IBM released two experimental preview models, granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview, built on Granite 4.1 base checkpoints and trained to read and write LLMON, an LLM-native markup language that uses reserved special-token delimiters to mark instructions, data and requirements. On the OPI benchmark, IBM says the models avoid 47% more indirect prompt injection attacks than the best frontier model tested and 95% more than the best open-source model, while matching Granite 4.1 Instruct on standard benchmarks. The release ships a GitHub toolkit with lossless JSON-to-LLMON converters. IBM describes the preview as for exploration, not production use.
Generated from reports · updated 16 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hugging Face BlogPicksIBM releases LLMON preview models built on Granite 4.1 3B and 8B
IBM released two experimental preview models, granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview, derived from Granite 4.1 base checkpoints and trained to consume and generate LLMON, an LLM-native markup language that marks instructions, data and requirements with reserved special-token delimiters. On the OPI benchmark the models avoid 47% more indirect prompt injection attacks than the best frontier model tested and 95% more than the best open-source model, while performing on par with Granite 4.1 Instruct on standard benchmarks. The release includes a GitHub toolkit with lossless JSON-to-LLMON converters, and the authors note the preview is for exploration, not production.
Heat for this event
Not enough continuous observations yet to draw a trend.