conftrace_

parameter-efficient reinforcement learning

2 papers

Explore in graph

Also known as

PE-RL

Co-occurring keywords · papers mentioning both

large language model (2) neutral point of view (1) impartial generation (1) impartial content (1) multilingual safety (1) prompt classification (1) group relative policy optimization (1) llm alignment (1) jailbreak detection (1) harmful content detection (1)

Papers

Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL EMNLP 2025 MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety EMNLP 2025