Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue
Year: 2026
Type: conference-paper
Abstract: We model utterance production as probabilistic cost-sensitive choice over contextual alternatives, using information-theoretic notions of cost.We distinguish between goal-directed alternatives that realise a fixed communicative intent and goal-agnostic alternatives defined only by contextual plausibility, allowing us to derive speaker-and listener-oriented interpretations of different cost measures.We present a procedure to generate both types of alternative sets using language models.Analysing production choices in open-ended dialogue under both deterministic and probabilistic cost minimisation, we find that surprisal minimisation relative to goal-directed alternatives provides the strongest predictive account under both analyses.By contrast, uniform information density and length-based costs exhibit weaker and less consistent predictive power across conditions.More broadly, our study suggests that alternative-conditioned optimisation with LMgenerated alternatives provides a principled framework for studying speaker and listener pressures in naturalistic language production. 1
Institutions: University of Aberdeen, University College London
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166865112