Research map / Large language models / Retrieval and knowledge
CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care
Tong Xiang, Liangzhi Li, Wangyue Li, Mingbai Bai, Lu Wei, Bowen Wang, Noa Garcia
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 |
|---|---|---|---|
| add retrieved knowledge to judgment model fine-tuning (ablation) | LLaMA-13B-T judgment model · validation set (correctness) | Pearson correlation: 0.779 -> 0.868 | Improved |
| add retrieved knowledge to judgment model fine-tuning (ablation) | LLaMA-13B-T judgment model · validation set (correctness) | accuracy: 0.806 -> 0.898 | Improved |
| add retrieved knowledge to judgment model fine-tuning (ablation) | LLaMA-13B-T judgment model · validation set (interpretability) | Pearson correlation: 0.639 -> 0.683 | Improved |
| add retrieved knowledge to judgment model fine-tuning (ablation) | LLaMA-13B-T judgment model · validation set (interpretability) | accuracy: 0.867 -> 0.835 | Hurt |
| use 2M instead of 0.2M instruction samples for BELLE-7B fine-tuning | BELLE-7B · CARE-MI correctness | correctness: 0.670 -> 0.647 | No clear effect |
| use 2M instead of 0.2M instruction samples for BELLE-7B fine-tuning | BELLE-7B · CARE-MI interpretability | interpretability: 0.645 -> 0.728 | Improved |
| replace BERT-Large with LLaMA-13B-T as judgment backbone | judgment model · validation set (correctness) | Pearson correlation: 0.606 -> 0.868 | Improved |
| replace BERT-Large with LLaMA-13B-T as judgment backbone | judgment model · validation set (interpretability) | Pearson correlation: 0.013 -> 0.683 | Improved |
| scale GPT-3 judgment model from 350M to 6.7B | judgment model · validation set (correctness) | Pearson correlation: 0.783 -> 0.803 | Improved |
| scale GPT-3 judgment model from 350M to 6.7B | judgment model · validation set (interpretability) | Pearson correlation: 0.565 -> 0.634 | Improved |
| use GPT-4 instead of GPT-3.5-turbo as the evaluated LLM | CARE-MI evaluation · CARE-MI correctness | correctness: 0.824 -> 0.867 | Improved |
| use ChatYuan instead of ChatGLM-6B for question generation | BIOS question generation · BIOS pilot | accuracy: 0.28 -> 0.79 | Improved |
Closest papers by meaning
- MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models (AAAI 2024 · similarity 0.89)
- MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey (NeurIPS 2024 · similarity 0.89)
- Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias (NeurIPS 2024 · similarity 0.88)
- CareBot: A Pioneering Full-Process Open-Source Medical Language Model (AAAI 2025 · similarity 0.87)
- Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks (NeurIPS 2026 · similarity 0.87)
- PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications (NeurIPS 2024 · 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.
