Ai2Labs
StateBench: Testing how language models track state changes over long documents

StateBench tests how language models track changing information across long documents at four difficulty levels, revealing where models struggle and how targeted training helps recurrent and hybrid…
Read at Ai2 ↗More from Ai2 on Accept All

LabsHow Olmo 3 earned the highest ethical rating from Nextcloud Ai2

LabsHow researchers are adapting olmOCR 2 for historical and archaeological archives Ai2

LabsCan we trust LLMs to judge whether a research idea is novel? Ai2

LabsLitPivot: Developing research ideas through dynamic contextualization within the literature landscape Ai2
LabsOlmoEarth v1.3: State-of-the-art embeddings for the whole planet Ai2
