From the 1 of 16 linked papers with an AI index.
16 papers
Where did the ambiguity go? Examining how multimodal models interpret polysemous words
Jasin Cekinmez, Addison J. Wu, Raja Marjieh +1
Human language is highly polysemous. Many common words (e.g., "bank" or "palm") carry several distinct meanings that shape what humans communicate and imagine. Large language model…
Human-AI Synergy Supports Collective Creative Search
Chenyi Li, Raja Marjieh, Haoyu Hu +4
The paper investigates how humans and generative AI can work together in a word‑guessing game, finding that hybrid human‑AI teams achieve higher performance while maintaining diver…
Popularity Feedback Constrains Innovation in Cultural Markets
Lucas Gautheron, Raja Marjieh, Dalton C. Conley +5
Real-world creative processes ranging from art to science rely on social feedback-loops between selection and creation. Yet, the effects of popularity feedback on collective creati…
An Experimental Method to Study Opinion Diffusion in Human-AI Hybrid Societies
Léna Gaubert, Rémi Devaux, Elif Ãelen +4
As artificial intelligence increasingly mediates public discourse, it becomes important to understand how human-AI collectives shape opinion formation, deliberation, and democratic…
Levels of Analysis for Large Language Models
Alexander Y. Ku, Declan Campbell, Xuechunzi Bai +10
Modern artificial intelligence systems, such as large language models, are increasingly powerful but also increasingly hard to understand. Recognizing this problem as analogous to…
Large Language Models provide support for the parallelogram theory of analogy
Qiawen Ella Liu, Raja Marjieh, Jian-Qiao Zhu +2
Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D. Recent work suggests that this model poorly capture…