BARRED uses dimension decomposition and asymmetric multi-agent debate to generate high-fidelity synthetic data that lets small fine-tuned models outperform proprietary LLMs and existing guardrail models on custom policies.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate
BARRED uses dimension decomposition and asymmetric multi-agent debate to generate high-fidelity synthetic data that lets small fine-tuned models outperform proprietary LLMs and existing guardrail models on custom policies.