Known Intents, New Combinations: Clause-Factorized Decoding for Compositional Multi-Intent Detection

ArXi:2603.28929v1 Announce Type: new Multi-intent detection papers usually ask whether a model can recover multiple intents from one utterance. We ask a harder and, for deployment, useful question: can it recover new combinations of familiar intents? Existing benchmarks only weakly test this, because train and test often share the same broad co-occurrence patterns. We