用 Jev 重打 2.3K 篇 AI 论文标签：83 秒花 0.14 美元
Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The ...
2300 篇论文重打标签只要 0.14 美元、83 秒，抽检 30 处分歧全采纳，做内容分类的可以参考这套组合。
DAIR.AI 创始人 Elvis Saravia 用 Jev 重新整理约 2.3K 篇 AI 研究论文的分类标签，全程 83 秒、总成本 0.14 美元。这批论文旧标签由开源模型 DeepSeek V4 Flash 生成，他对质量没有把握，而用 few-shot 调一个可靠分类器成本更高。Jev 重打标签后与旧标签一致率为 75%，标出约 579 处高置信度的主题变更。他人工核验其中 30 处分歧并全部采纳，改动已上线 academy.dair.ai/papers。他的结论是把 System One 和 System Two 两类模型组合进流水线能明显改进分类效果。
Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The ...
Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which I ran through a previous open model (DeepSeek V4 Flash). However, I wasn't confident in the classifications, and I didn't want to spend more on tokens unless I spent time tuning it into a good LLM classifier via few-shot (more expensive). Too tedious, too costly, and unsustainable. Luckily for us, we now have Jev to help us with organizing papers better. So Jev first went through all the papers and retagged them. It agreed with 75% of the previous tags. Jev found about 579 high-confidence topic changes. I evaluated reliability by manually labeling 30 disagreements and accepted all of them. I was astonished by Jev's classification capabilities. We applied and verified all changes in production. I'm much more satisfied with the classifications, but I think there is still room for improvement. Check out the papers here: academy.dair.ai/papers I will experiment with Jev more. The takeaway is that pipelines can be significantly improved by carefully combining System One and System Two models. Jev clearly unlocks more interesting ways to organize papers and offer a more useful discovery layer for research papers. More updates on that soon. Your browser does not support the video tag. 🔗 View on Twitter 💬 4 🔄 1 ❤️ 6 👀 1091 📊 5 ⚡
