latent-im-91b0d99c·1 events·first seen Aliases: Latent-IM
Researchers introduce Latent-IM, a framework that recovers an internal analogue of classical dialogue management (state estimation and action control) within LLMs for spoken dialogue systems. The approach formulates conversational move control as two coupled problems—selection and realization—and provides a general interface for steering conversational moves at generation time without full fine-tuning. On the task of reproducing human conversational move choices, Latent-IM improves average end-to-end move accuracy by 12.5 points over an unsteered backbone while matching fine-tuning performance.