MultistakeholderAI
Collection
Foundational multimodal corpus for provenance-preserving, multistakeholder AI deliberation research in digital policy and Internet governance. • 4 items • Updated
Arwen Policy Base
Base language model for the Arwen Policy project — an evidence-grounded, multistakeholder AI deliberation system for digital policy and Internet governance.
Model
This repository packages the Arwen Policy configuration for use with Qwen 3 via Ollama. The model is configured for evidence-grounded policy analysis with a 40K context window, low temperature (0.2), and a system prompt that instructs the model to attribute claims to documented sources, preserve stakeholder disagreements, disclose missing perspectives, and never manufacture consensus or evidence.
Intended Use
- Evidence-grounded policy synthesis
- Stakeholder-aware argument analysis
- Multistakeholder deliberation
- Policy recommendation generation with provenance
Training
This is the base Qwen 3 model with an Arwen Policy system prompt and inference configuration. It has not been fine-tuned on the Arwen Policy Corpus.
For the task-adapted version, see Arwen Policy LoRA.
Links
- Dataset: https://huggingface.co/datasets/soyames/arwen-policy-corpus
- LoRA adapter: https://huggingface.co/soyames/arwen-policy-lora
- Interactive demo: https://huggingface.co/spaces/soyames/arwen-policy
- Source code: https://github.com/soyames/arwen-policy
Citation
See CITATION.cff in the project repository.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support