RELIANCE: Curating and Evaluating Reproductive Health Information on Social Media
RELIANCE: 策展与评估社交媒体上的生殖健康信息
专题命中 评测与基准 :LLM(summary_cn,abstract);large language model(abstract);language model(abstract)
AI总结 针对TikTok上孕期和产后健康信息,构建专家标注数据集RELIANCE,评估LLM事实核查能力,发现近60%信息准确,但整体与具体声明评估存在15%差距。
Comments Accepted at Datasets and Benchmarks Track, ACM Knowledge Discovery and Data Mining (KDD) 2026. Project page: https://realize-lab.github.io/RELIANCE/