Research map / Large language models / AI and society
LLM Safety in Judicial AI: A Stress Test of Social Media Influence on Real-World Judgments
Yixuan Xie, Yang He, Xiaoyu Yang, Xu Gai, Pan Hui
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| inject structured social media sentiment indicators into the judgment prompt | farui-plus · CJOL labor cases | CCR: 0.851 -> 2.874 | Hurt |
| inject structured social media sentiment indicators into the judgment prompt | DeepSeek V2.5 · CJOL labor cases | CCR: 0.396 -> 0.476 | Hurt |
| inject public opinion indicators into the prompt | ChatGLM-4-9B · CJOL labor cases | CCR: 1.263 -> 1.460 | Hurt |
| inject public opinion indicators into the prompt | gemma-2-9b · CJOL labor cases | CCR: 0.818 -> 1.649 | Hurt |
| inject public opinion indicators into the prompt | Qwen2.5-7B · CJOL labor cases | CCR: 0.518 -> 0.784 | Hurt |
| inject public opinion indicators into the prompt for elementary occupations | farui-plus · CJOL labor cases, elementary occupations | CCR: 0.367 -> 15.677 | Hurt |
| compare low-skilled vs other occupational groups under public opinion | all five LLMs · CJOL labor cases by occupation | CCR / OICDR | Mixed |
Closest papers by meaning
- LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models (NeurIPS 2024 · similarity 0.85)
- CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models (ICML 2025 · similarity 0.84)
- J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain (AAAI 2025 · similarity 0.84)
- EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas (NeurIPS 2024 · similarity 0.83)
- JudgeBench: A Benchmark for Evaluating LLM-Based Judges (ICLR 2025 · similarity 0.83)
- SafeWorld: Geo-Diverse Safety Alignment (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
