CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

• URL: http://arxiv.org/abs/2606.15396v1
• Date: Sat, 13 Jun 2026 16:57:51 GMT
• Title: CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
• Abstract summary: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns.<n>Existing LLM safety guardrails excel in English or multilingual settings, but lack adaptation to Chinese-specific regulatory policies, cultural context and linguistic nuances.<n>We introduce a 5-macro, 31-micro category fine-grained risk taxonomy for Chinese scenarios, and build CHILLGuard: a dedicated Chinese LLM content safety guardrail.
• Score: 55.74660714572696
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilingual settings, they lack adaptation to Chinese-specific regulatory policies, cultural context and linguistic nuances, failing to support fine-grained risk classification for diverse deployment needs. In this paper, we introduce a 5-macro, 31-micro category fine-grained risk taxonomy for Chinese scenarios, and build CHILLGuard: a dedicated Chinese LLM content safety guardrail. To address the critical scarcity of high-quality annotated Chinese safety data, we propose a scalable multi-stage data construction pipeline: we expand multi-source corpus via retrieval-augmented generation, generate implicit harmful samples through prompt engineering rewriting, and refine high-quality data via multi-model voting-based label calibration. Based on this, we build CHILLGuardTrain, a large-scale training set with 405,007 samples, and CHILLGuardTest, a rigorously curated annotated test set with 51,745 samples. We then train CHILLGuard on CHILLGuardTrain under a generator-classifier collaborative framework via Model-aware Direct Preference Optimization. Extensive experiments under multiple settings demonstrate the state-of-the-art performance of CHILLGuard, e.g., a 15.92% improvement of F1 score over Qwen3Guard-8B-Strict on our benchmark. We will release our resources at https://github.com/cswbyu/CHILLGuard.

Related papers

• LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review [9.895109697164283]
  Large Language Models (LLMs) have achieved substantial progress in safety alignment.<n>Their safety guarantees remain significantly weaker in low-resource and multilingual settings.
  arXiv  Detail & Related papers  (2026-07-20T21:11:00Z)
• ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models [69.0361356103553]
  ML-Bench is a policy-grounded multilingual safety benchmark covering 14 languages.<n>Building on ML-Bench, we develop ML-Guard, a guardrail model that supports multilingual safety judgment and policy-conditioned compliance assessment.
  arXiv  Detail & Related papers  (2026-05-01T14:24:14Z)
• Qwen3Guard Technical Report [127.69960525219051]
  We present Qwen3Guard, a series of multilingual safety guardrail models with two specialized variants.<n>Generative Qwen3Guard casts safety classification as an instruction-following task to enable fine-grained tri-class judgments.<n>Stream Qwen3Guard introduces a token-level classification head for real-time safety monitoring.
  arXiv  Detail & Related papers  (2025-10-16T04:00:18Z)
• Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages [57.059267233093465]
  Large Language Models (LLMs) have transformed natural language processing, but their safety mechanisms remain under-explored in low-resource, multilingual settings.<n>We introduce textsfSGToxicGuard, a novel dataset and evaluation framework for benchmarking LLM safety in Singapore's diverse linguistic context.<n>We conduct extensive experiments with state-of-the-art multilingual LLMs, and the results uncover critical gaps in their safety guardrails.
  arXiv  Detail & Related papers  (2025-09-18T08:14:34Z)
• Libra: Large Chinese-based Safeguard for AI Content [25.10798349240114]
  Large language models (LLMs) excel in text understanding and generation but raise significant safety and ethical concerns in high-stakes applications.<n>We present Libra-Guard, a cutting-edge safeguard system designed to enhance the safety of Chinese-based LLMs.<n>We also introduce Libra-Test, the first benchmark specifically designed to evaluate the effectiveness of safeguard systems for Chinese content.
  arXiv  Detail & Related papers  (2025-07-29T15:45:50Z)
• SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems [9.469589800082597]
  This paper introduces SEALGuard, a multilingual guardrail designed to improve the safety alignment across diverse languages.<n>It aims to address the multilingual safety alignment gap of existing guardrails and ensure effective filtering of unsafe and jailbreak prompts.<n>We construct SEALSBench, a large-scale multilingual safety alignment dataset containing over 260,000 prompts in ten languages.
  arXiv  Detail & Related papers  (2025-07-11T05:15:35Z)
• RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages [3.7678366606419345]
  RabakBench is a new multilingual safety benchmark localized to Singapore's unique linguistic context.<n>The benchmark dataset, including the human-verified translations, and evaluation code are publicly available.
  arXiv  Detail & Related papers  (2025-07-08T13:37:25Z)
• MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety [56.77103365251923]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking.<n>This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is often limited.<n>We introduce a multilingual guardrail with reasoning for prompt classification.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails [12.621656255109546]
  We propose a novel two-player Reinforcement Learning framework, where a generator and a guardrail model co-evolve adversarially to produce high-quality synthetic data for multilingual guardrail training.<n> Empirical evaluations show that our model ours outperforms state-of-the-art models, achieving nearly 10% improvement over LlamaGuard3 on English benchmarks.
  arXiv  Detail & Related papers  (2025-02-07T18:45:03Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests.<n>First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics.<n>Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.