热点
"事实性评估" 相关文章
FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality
cs.AI updates on arXiv.org 2025-08-04T04:27:30.000000Z
让「幻觉」无处遁形！谷歌DeepMind全新基准，三代Gemini同台霸榜
智源社区 2025-01-14T09:05:19.000000Z