Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue

2026-05-01 · Tom Utting, Mario Giulianelli, Arabella Sinclair arxiv

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 LM-generated alternatives provides a principled framework for studying speaker and listener pressures in naturalistic language production.

📄 PDF Abstract BibTeX arXiv:2605.00506

Code (0)

등록된 구현이 없습니다.

MIME: Mutual Information Minimisation Exploration

2020-01-16 · Haitao Xu, Brendan McCane, Lech Szymanski, Craig Atkinson

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solut…

Montezuma's Revenge reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Articulation rate in Swedish child-directed speech increases as a function of the age of the child even when surprisal is controlled for

2017-06-10 · Johan Sjons, Thomas Hörberg, Robert Östling, Johannes Bjerva

In earlier work, we have shown that articulation rate in Swedish child-directed speech (CDS) increases as a function of the age of the child, even when utterance length and differences in articulation rate between subjec…

Information Value: Measuring Utterance Predictability as Distance from Plausible Alternatives

2023-10-20 · Mario Giulianelli, Sarenne Wallbridge, Raquel Fernández

We present information value, a measure which quantifies the predictability of an utterance relative to a set of plausible alternatives. We introduce a method to obtain interpretable estimates of information value using …

Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning

2020-04-23 · Giambattista Parascandolo, Lars Buesing, Josh Merel, Leonard Hasenclever 외

Standard planners for sequential decision making (including Monte Carlo planning, tree search, dynamic programming, etc.) are constrained by an implicit sequential planning assumption: The order in which a plan is constr…

continuous-control Continuous Control Decision Making Reinforcement Learning+2

Surprisal Theory is Tautological (without Rational Grounding)

2026-07-23 · Ryan Cotterell arxiv

Surprisal theory holds that the human processing difficulty of a linguistic unit in context is an affine function of its surprisal under some language model. I argue this claim is a tautology without further constraint: …