Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models
Text from multiple sources can become interleaved into a single sequence when attribution metadata is lost, such as overlapping speech transcripts, document reading flows, or concurrent agent streams. We formalize this challenge as Word-Level Text Unmixing: given an interleaved lexical stream and source count K, recove...
Jin-Ling He, Si-Yang Jiang, Li-Xing He et al.
· 0 citations