Topic: large language models

37 stories found

Today

research40

TimeCapsule: Generative Hallucination as a Method for Historical Sensemaking

TimeCapsule is a new method using a large language model to address the temporal bias in contemporary training data, making these models unreliable for historical contexts. The researchers developed TimeCapsule, a 1.2B-parameter model, to better handle historical sensemaking by reducing present-day concept encoding.

arxiv.org↗

Wednesday, July 22, 2026

🌿 That's all for now. Come back tomorrow.

37 of 37 items shown. Sources: 70 days indexed.