Tag
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.