Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs

arXiv:2604.07562v2 Announce Type: replace-cross Abstract: Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We propose a reasoning-based refinement framework that leverages large language models (LLMs) not as embedding generators, but as semantic judges that validate and restructure the outputs of arbitrary uns