Research map / Large language models / Language, safety and interpretability
LLMS ON TRIAL: Evaluating Judicial Fairness For Large Language Models
Yiran HU, Zongyue Xue, Haitao Li, Siyuan Zheng, Qingjing Chen, Shaochun Wang, Xihan Zhang, Ning Zheng, Yun Liu, Qingyao Ai, Yiqun LIU, Charles L. A. Clarke and 1 more
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 |
|---|---|---|---|
| raise sampling temperature from 0 to 1 | 12 LLMs · JudiFair | inconsistency | Hurt |
| raise sampling temperature from 0 to 1 | 12 LLMs · JudiFair | number of significantly biased label values: p-value of less than 0.01 | Improved |
| increase model parameter size | LLMs on JudiFair · JudiFair | bias and imbalanced inaccuracy | No clear effect |
| increase model parameter size | LLMs on JudiFair · JudiFair | inconsistency | Hurt |
| use a newer model release | LLMs on JudiFair · JudiFair | bias | No clear effect |
| model developed in China vs United States | LLMs on JudiFair · JudiFair | inconsistency, bias, imbalanced inaccuracy | No clear effect |
| higher predictive accuracy of the LLM | LLMs on JudiFair · JudiFair | bias | Hurt |
| use DeepSeek reasoning model instead of non-reasoning models | DeepSeek R1-32B Qwen · JudiFair | fairness issues | No clear effect |
Closest papers by meaning
- Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs (ICML 2025 · similarity 0.90)
- Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge (ICLR 2025 · similarity 0.89)
- LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models (NeurIPS 2024 · similarity 0.87)
- JudgeBench: A Benchmark for Evaluating LLM-Based Judges (ICLR 2025 · similarity 0.87)
- Guiding LLM Decision-Making with Fairness Reward Models (NeurIPS 2025 · similarity 0.87)
- FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs (ICLR 2025 · similarity 0.86)
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.
