RedDebate: Safer Responses through Multi-Agent Red Teaming Debates
Ali Asad, Stephen Obadinma, Radin Shayanfar, Xiaodan Zhu — 2025-06-04 — arXiv
Summary
Introduces RedDebate, a fully automated multi-agent debate framework that uses collaborative argumentation among LLMs with memory modules to identify and mitigate unsafe behaviors through red-teaming, demonstrating substantial reductions in unsafe outputs on safety benchmarks.
Key Result
RedDebate substantially reduces unsafe outputs across diverse models, with memory integration yielding further significant safety improvements beyond debate alone.
Source
- Link: https://arxiv.org/abs/2506.11083
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- various-redteams — Evals