# Libra: Large Chinese-based Safeguard for AI Content

arXiv: https://arxiv.org/abs/2507.21929 · HTML: https://mlsanity.com/paper/2507.21929/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [Safety Assessment of Chinese Large Language Models](https://mlsanity.com/paper/2304.10436/) (2023)
- [AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications](https://mlsanity.com/paper/2311.08592/) (2023)
- [ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors](https://mlsanity.com/paper/2402.16444/) (2024)
- [From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2401.02777/) (2024)
- [SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.08989/) (2025)
- [NExtLong: Toward Effective Long-Context Training without Long Documents](https://mlsanity.com/paper/2501.12766/) (2025)
- [Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model](https://mlsanity.com/paper/2405.19846/) (2024)
- [CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning](https://mlsanity.com/paper/2410.02229/) (2024)
- [Task Oriented In-Domain Data Augmentation](https://mlsanity.com/paper/2406.16694/) (2024)
- [LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions](https://mlsanity.com/paper/2505.17134/) (2025)
- [Structured Probabilistic Coding](https://mlsanity.com/paper/2312.13933/) (2023)

## Built on by (most cited first, 2 of 2)

- [CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns](https://mlsanity.com/paper/2601.00588/) (2026)
- [LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails](https://mlsanity.com/paper/2608.27580/) (2026)

## Abstract (arXiv)

Large language models (LLMs) excel in text understanding and generation but raise significant safety and ethical concerns in high-stakes applications. To mitigate these risks, we present Libra-Guard, a cutting-edge safeguard system designed to enhance the safety of Chinese-based LLMs. Leveraging a two-stage curriculum training pipeline, Libra-Guard enhances data efficiency by employing guard pretraining on synthetic samples, followed by fine-tuning on high-quality, real-world data, thereby significantly reducing reliance on manual annotations. To enable rigorous safety evaluations, we also introduce Libra-Test, the first benchmark specifically designed to evaluate the effectiveness of safeguard systems for Chinese content. It covers seven critical harm scenarios and includes over 5,700 samples annotated by domain experts. Experiments show that Libra-Guard achieves 86.79% accuracy, outperforming Qwen2.5-14B-Instruct (74.33%) and ShieldLM-Qwen-14B-Chat (65.69%), and nearing closed-source models like Claude-3.5-Sonnet and GPT-4o. These contributions establish a robust framework for advancing the safety governance of Chinese LLMs and represent a tentative step toward developing safer, more reliable Chinese AI systems.