Tag
This paper proves that there is no theoretical curse of multilinguality for embedding space structure, showing that the minimum dimensionality required grows only logarithmically with the number of languages, suggesting empirical issues stem from data and training conditions.
The paper introduces Topological Void Analysis (TVA), a mathematical framework that formalizes the discovery of unexplored technical regions in high-dimensional knowledge spaces by identifying triads of concepts with specific cohesion and marginality conditions. Applied to ~140k documents, TVA generates invention candidates with high survival rates through expert review.
Researchers from KTH Royal Institute of Technology propose a two-stage framework that fine-tunes LLMs on dialogue transcripts and uses contrastive learning to create joint embeddings for aligning backchannel signals with conversational context, demonstrating improved context-backchannel retrieval compared to previous methods.