MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insights
About
Multilingual and multicultural benchmarks now cover dozens of languages and model families, but the resulting score landscapes remain metric-rich and insight-poor, necessitating fine-grained multilingual post-evaluation diagnosis. However, single LLMs and open-ended agents are easily swamped by the long, noisy diagnostic input, and no reusable taxonomy exists for it. To address this, we propose MADE, a Multilingual Agentic Diagnosing Engine that decomposes post-evaluation analysis into planning, aggregate analysis, instance-level case inspection, multilingual and cultural reflection, and grounded report synthesis. MADE is paired with an expert-led 54-query and 15-language diagnostic set, evaluated on top of a large-scale multilingual evaluation substrate (33 model families, 11 benchmarks, 26 languages, 34 cultures, 8.66M evaluation records). Experiments show that MADE outperforms the strongest shared baseline by 47% in diagnosis report quality and is preferred by human multilingual experts in 87.9% of pairwise comparisons. Applied with multilingual experts, MADE further surfaces four actionable findings on deployment, iteration, and cross-cultural pitfalls, turning benchmark score tables into model-selection and remediation guidance.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Multilingual Diagnostic Report Generation | Multilingual Diagnosis 15-language setting (54 queries/language) | Performance Score (ZH)8.08 | 8 | |
| Diagnostic report generation | Human-Eval 12-language (120 items) | Human Mean Score7.41 | 3 | |
| Pairwise Report Evaluation | Human Evaluation Arabic N=10 | Win Rate77.5 | 3 | |
| Pairwise Report Evaluation | Human Evaluation German N=10 (de) | Win Rate95 | 3 | |
| Pairwise Report Evaluation | Human Evaluation English N=10 | Win Rate80 | 3 | |
| Pairwise Report Evaluation | Human Evaluation French N=10 | Win Rate65 | 3 | |
| Pairwise Report Evaluation | Human Evaluation Italian N=10 | Win Rate90 | 3 | |
| Pairwise Report Evaluation | Human Evaluation Korean N=10 | Win Rate95 | 3 | |
| Pairwise Report Evaluation | Human Evaluation Polish N=10 | Win Rate90 | 3 | |
| Pairwise Report Evaluation | Human Evaluation Portuguese N=10 (pt) | Win Rate97.5 | 3 |