AI Paper Atlas

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

NeurIPS 2023 · Large language models › Retrieval and knowledge · approach: Knowledge-augmented question answering · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
add retrieved knowledge to judgment model fine-tuning (ablation)LLaMA-13B-T judgment model · validation set (correctness)Pearson correlation: 0.779 -> 0.868Improved
add retrieved knowledge to judgment model fine-tuning (ablation)LLaMA-13B-T judgment model · validation set (correctness)accuracy: 0.806 -> 0.898Improved
add retrieved knowledge to judgment model fine-tuning (ablation)LLaMA-13B-T judgment model · validation set (interpretability)Pearson correlation: 0.639 -> 0.683Improved
add retrieved knowledge to judgment model fine-tuning (ablation)LLaMA-13B-T judgment model · validation set (interpretability)accuracy: 0.867 -> 0.835Hurt
use 2M instead of 0.2M instruction samples for BELLE-7B fine-tuningBELLE-7B · CARE-MI correctnesscorrectness: 0.670 -> 0.647No clear effect
use 2M instead of 0.2M instruction samples for BELLE-7B fine-tuningBELLE-7B · CARE-MI interpretabilityinterpretability: 0.645 -> 0.728Improved
replace BERT-Large with LLaMA-13B-T as judgment backbonejudgment model · validation set (correctness)Pearson correlation: 0.606 -> 0.868Improved
replace BERT-Large with LLaMA-13B-T as judgment backbonejudgment model · validation set (interpretability)Pearson correlation: 0.013 -> 0.683Improved
scale GPT-3 judgment model from 350M to 6.7Bjudgment model · validation set (correctness)Pearson correlation: 0.783 -> 0.803Improved
scale GPT-3 judgment model from 350M to 6.7Bjudgment model · validation set (interpretability)Pearson correlation: 0.565 -> 0.634Improved
use GPT-4 instead of GPT-3.5-turbo as the evaluated LLMCARE-MI evaluation · CARE-MI correctnesscorrectness: 0.824 -> 0.867Improved
use ChatYuan instead of ChatGLM-6B for question generationBIOS question generation · BIOS pilotaccuracy: 0.28 -> 0.79Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy