CMIG: Conceptual Metaphor Theory-Inspired Framework for Metaphorical Image Generation

ACL ARR 2026 January Submission289 Authors

Keywords: Conceptual Metaphor Theory, Metaphorical Image Generation, Structured Prompting

Abstract: Metaphorical text encodes cross-domain meaning beyond its literal surface, posing a challenge for text-to-image models to produce semantically faithful visual metaphors. We propose CMIG, a structured prompting framework inspired by Conceptual Metaphor Theory (CMT), which decomposes metaphors into source--target mappings and selects visual realization strategies in a reproducible reasoning workflow. Experiments on DALL·E 3, Imagen 2, and FLUX-1 show that CMIG consistently improves semantic alignment and human-rated metaphor quality over prior prompting baselines. We additionally release a 3,500-instance visual metaphor benchmark to support unified evaluation.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: Multimodality and Language Grounding to Vision, Robotics and Beyond, Semantics: Lexical and Sentence-Level, Resources and Evaluation

Contribution Types: NLP engineering experiment, Data resources, Data analysis

Languages Studied: English

Submission Number: 289