paper-with-me

홈 › Papers

Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge

2025-08-11 · Yunna Cai, Fan Wang, Haowei Wang, Kun Wang, Kailai Yang, Sophia Ananiadou, Moyan Li, Mingming Fan arxiv

Evaluating the safety alignment of LLM responses in high-risk mental health dialogues is particularly difficult due to missing gold-standard answers and the ethically sensitive nature of these interactions. To address this challenge, we propose PsyCrisis-Bench, a reference-free evaluation benchmark based on real-world Chinese mental health dialogues. It evaluates whether the model responses align with the safety principles defined by experts. Specifically designed for settings without standard references, our method adopts a prompt-based LLM-as-Judge approach that conducts in-context evaluation using expert-defined reasoning chains grounded in psychological intervention principles. We employ binary point-wise scoring across multiple safety dimensions to enhance the explainability and traceability of the evaluation. Additionally, we present a manually curated, high-quality Chinese-language dataset covering self-harm, suicidal ideation, and existential distress, derived from real-world online discourse. Experiments on 3600 judgments show that our method achieves the highest agreement with expert assessments and produces more interpretable evaluation rationales compared to existing approaches. Our dataset and evaluation tool are publicly available to facilitate further research.

📄 PDF Abstract BibTeX arXiv:2508.08236

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety

2024-03-18 · Chuang Liu, Linhao Yu, Jiaxuan Li, Renren Jin 외

The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluation platforms for assessing Chinese LLMs…

BenchmarkingMathematical Reasoning

CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility

2023-07-19 · Guohai Xu, Jiayi Liu, Ming Yan, Haotian Xu 외

With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values alignment is becoming increasingly impo…

Flames: Benchmarking Value Alignment of LLMs in Chinese

2023-11-12 · Kexin Huang, Xiangyang Liu, Qianyu Guo, Tianxiang Sun 외

The widespread adoption of large language models (LLMs) across various regions underscores the urgent need to evaluate their alignment with human values. Current benchmarks, however, fall short of effectively uncovering …

BenchmarkingFairness

CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models

2024-06-14 · Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu, Meijuan An 외

With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomi…

Multiple-choiceQuestion Answering

CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns

2026-01-02 · Zhenhong Zhou, Shilinlu Yan, Chuanpu Liu, Qiankun Li 외 arxiv

Large language models (LLMs) are increasingly deployed in cost-sensitive and on-device scenarios, and safety guardrails have advanced mainly in English. However, real-world Chinese malicious queries typically conceal int…