Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

arXiv:2609.01210 · cs.CR, cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-01

Updated: 2026-09-11

Code: https://github.com/SparkShieldLab/C-SafeQA

Terminology

• Benchmark — 80× in this paper · explained in 2 episodes
• Robustness — 15× in this paper · explained in 5 episodes
• Actionability — 14× in this paper · explained in 3 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Alignment — 7× in this paper · explained in 1 episode
• Verifier — 7× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Adversarial Robustness — 3× in this paper · explained in 3 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 4 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Distribution Shift — 2× in this paper · explained in 6 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Adversarial Prompting — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
• Safety Assessment of Chinese Large Language Models
• CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility
• CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models
• ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Qwen3Guard Technical Report
• OR-Bench: An Over-Refusal Benchmark for Large Language Models
• JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
• YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models
• Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation
• HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
• A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
• BabelSafe: A Policy-Grounded Multilingual Safety Benchmark for LLMs
• GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models
• ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
• SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
• CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs