4 citations · 8 across the 5 of their papers we have counts for
4 papers · 1 filter
Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picture
Cody Kommers, Mingrui Ye, Evelyn Gius +4
Ambiguity is often treated as a bug for AI systems to resolve---but in human communication and culture, ambiguity can also be a generative resource. From humour to politics to art,…
The House with a Million Windows: Interactive Fiction for Narrative Restorying
Cody Kommers, Sarah G Immel, Drew Hemment +1
AI-assisted writing can flatten meaning in human storytelling, enabling the production of homogeneous outputs without the intentional effort and sense-making writing entails. To ad…
Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale
Cody Kommers, Drew Hemment, Maria Antoniak +4
This position paper argues that large language models (LLMs) can make cultural context, and therefore human meaning, legible at an unprecedented scale in AI-based sociotechnical sy…
Outperforming Word2Vec on Analogy Tasks with Random Projections
Abram Demski, Volkan Ustun, Paul Rosenbloom +1
We present a distributed vector representation based on a simplification of the BEAGLE system, designed in the context of the Sigma cognitive architecture. Our method does not requ…