Studies by Maina et al. identify persistent challenges in LLM-as-a-Judge methods, including verbosity bias, inconsistency in low-resource languages, and a 'severity gap' where models like GPT-5 and Gemini exhibit divergent leniency compared to human clinicians.

Authors

• Person: Not available Organization: arXiv
  A Comprehensive Benchmark and Evaluation Framework for Multi ...

Sources

• A Comprehensive Benchmark and Evaluation Framework for Multi ... arxiv.org arXiv via serper

Referenced by nodes (3)

• LLM-as-a-judge concept
• Gemini concept
• GPT-5 concept