Chinese contentAllenAI 发布 NoveltyBench：LLM 能否判断研究想法的新颖性
AllenAI 做了个叫 NoveltyBench 的测试，专门看 GPT、Claude 这类模型当'论文评审'时能不能看出一个 idea 是不是已经有人做过了，做科研的朋友可以看看结果。
#AllenAI
4 stories · 0 in 7 days · 2 in 30 days
Stories, products and papers tagged "AllenAI", newest first.
Oct 28
Oct 21
Chinese contentAllenAI 发布 FairStress：更深入评估 LLM 决策公平性
AllenAI 搞了个叫 FairStress 的公平性评测，专门测 LLM 做决策时会不会偏心，做模型评估的可以看看。
Oct 1
AllenAI launches Olmo-core 3
This open-source infrastructure democratizes access to MoE model training, potentially accelerating research beyond well-funded labs. Developers and researchers can now experiment with MoE architectures without massive resource requirements, though they'll still need significant GPU clusters for full-scale training.
Aug 13
Chinese contentAllenAI Open Instruct Tulu 3 后训练指南：SFT、DPO、RLVR、GRPO
想自己微调模型又没大显卡？这份教程教你在 16GB 显存上跑完 SFT、DPO、GRPO 全流程，用的还是 AllenAI 的开源框架。
