Search papers, labs, and topics across Lattice.
This paper introduces the Adaptive Pedagogical Vigilance (APV) framework, which redefines communicative vigilance as an adaptive mechanism for optimizing learning through intent inference in educational contexts. Utilizing a Bayesian Pedagogical Intent Inference Engine (PIIE), the framework models how instructors curate content to enhance pedagogical utility while enabling learners to infer instructional intents. Experimental results demonstrate that APV significantly boosts model vigilance in distinguishing pedagogical content from exposure-based content, achieving a high correlation with human judgments and outperforming baseline methods on naturalistic data.
APV enables LLMs to discern pedagogical intent with unprecedented accuracy, achieving a correlation of $r=0.958$ with human judgments.
The capacity of Large Language Models (LLMs) to reason about pedagogical intent within instructional communication remains underexplored, particularly in educational domains such as translation pedagogy. To address this, we propose the \textbf{Adaptive Pedagogical Vigilance (APV)} framework, a novel computational formalism that reframes communicative vigilance as an adaptive mechanism for optimizing learning through intent inference. APV formalizes the problem via a Bayesian Pedagogical Intent Inference Engine (PIIE), which models how instructors select content to maximize pedagogical utility and how vigilant learners should inversely reason about latent instructional configurations -- encompassing genre, stance, and incentives. We evaluate APV through a three-tier hierarchy: distinguishing instructional genre, reasoning about structured pedagogical setups, and generalizing to authentic educational discourse. Experiments on leading LLMs (e.g., GPT-4o, Claude 3.5) show that APV substantially improves model vigilance. It achieves the strongest discrimination between pedagogical and exposure-based content, correlates highly with human judgments ($r=0.958$), and maintains robust performance on naturalistic data where baseline methods degrade. This work establishes a unified framework for assessing and enhancing LLMs'understanding of pedagogical motives, advancing the development of more reliable AI-assisted learning systems.
