Information Dynamics of Language Communication
2026-06-29 • Computation and Language
Computation and LanguageInformation Theory
AI summaryⓘ
The authors created a new way to measure how meaning moves between people when they talk, using ideas from information theory. They use large language models to estimate how much one person's words predict another's, and to understand how different speakers contribute uniquely or together to the conversation. Their method worked in several tests, like spotting less meaningful exchange in rigid talks, showing who influences discussions more, and evaluating how therapists and clients share information. This tool can help study conversations in many fields, including education and therapy.
information theorysemantic transfer entropysemantic partial information decompositionlarge language modelsdialogue analysispredictive influenceredundant informationunique informationsynergistic informationcomputational linguistics
Authors
Leonardo S. Goodall, Andrea I. Luppi, Pedro A. M. Mediano
Abstract
Quantifying how meaning propagates through communicative exchanges remains underdeveloped in computational linguistics. Here we introduce an information-theoretic framework that quantifies the directed flow of semantic content between interlocutors and decomposes multi-source contributions into redundant, unique, and synergistic components. Our approach leverages large language models as probabilistic estimators of natural language to compute two measures: semantic transfer entropy (STE), which captures directed predictive influence between speakers, and semantic partial information decomposition (SPID), which resolves how multiple sources jointly shape a target's language. Across four experiments we show that the framework detects reduced information flow in cognitively rigid dialogue, captures the dominant role of persuaders in shaping discourse, distinguishes high- from low-quality psychotherapy by the directionality of therapist-client information exchange, and reveals synergistic premise contributions in argumentative essays. This framework opens new avenues for studying information dynamics in digital discourse, pedagogical interactions, clinical dialogues, and any domain in which the structure of linguistic exchange is of research relevance.