Bridging the Embodiment Gap in Agricultural Knowledge Representation for Language Models

Huijin Ju, Vasu Jindal, Zili Lyu

Keywords: Embodied cognition, language models, agricultural knowledge, sensorimotor grounding, knowledge representation, prompt engineering, sensory linguistics, tacit knowledge, metaphorical grounding, haptic vocabulary

TL;DR: Our dual computational frameworks transform how LLMs represent embodied agricultural knowledge, enabling these models to capture the rich sensory, procedural, and contextual expertise that farmers develop through physical experience.

Abstract: This paper quantifies the "embodiment gap" between disembodied language models and embodied agricultural knowledge communication through mixed-methods analysis with 78 farmers. Our key contributions include: (1) the Embodied Knowledge Representation Framework (EKRF), a novel computational architecture with specialized lexical mapping that incorporates embodied linguistic patterns from five identified domains of agricultural expertise; (2) the Embodied Prompt Engineering Protocol (EPEP), which reduced the embodiment gap by 47.3\% through systematic linguistic scaffolding techniques; and (3) the Embodied Knowledge Representation Index (EKRI), a new metric for evaluating embodied knowledge representation in language models. Implementation results show substantial improvements across agricultural domains, with particularly strong gains in tool usage discourse (58.7\%) and soil assessment terminology (67\% reduction in embodiment gap). This research advances both theoretical understanding of embodied cognition in AI and practical methodologies to enhance LLM performance in domains requiring embodied expertise.

Archival Status: Archival

Paper Length: Long Paper (up to 8 pages of content)

Submission Number: 247