Can Language Models Imagine Without Seeing? EKPHRASIS: Measuring Visual Creative Ideation in Text-Only LLMs

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


MPhil Thesis Defence


Title: "Can Language Models Imagine Without Seeing? EKPHRASIS: Measuring 
Visual Creative Ideation in Text-Only LLMs"

By

Mr. Hongyu LUO


Abstract:

Current evaluations do not isolate whether text-only language models can 
originate visual concepts before image generation. Fluent visual prose can 
hide visual-plan failures: an answer may appear creative while repeating 
familiar visual cliches or failing to specify a renderable scene. We define 
Visual Creative Ideation (VCI) as the ability to produce textual visual plans 
that are useful, expressive, and population-novel, and introduce EKPHRASIS, a 
400-task benchmark spanning Abstraction, Combination, Transformation, and 
Adaptation. EKPHRASIS scores anonymized pairwise comparisons with 
dimension-specific checklists, aggregates preferences with Bradley-Terry 
models, and uses Typed Idea Graphs to convert task-specific population cliches 
into novelty references. Across 14 language models, VCI separates usefulness, 
expressiveness, and novelty rather than reducing to fluency: strong models 
achieve similar overall scores through different profiles, and useful plans 
can remain visually clichd. A cross-modal grounding study further shows that 
text-level VCI ordering largely survives faithful rendering and blind 
image-level preference judgment, supporting EKPHRASIS as a measure of visual 
ideation beyond prose quality.


Date:                   Monday, 17 August 2026

Time:                   12:00noon - 2:00pm

Venue:                  Room 2132C
                        Lift 22

Chairman:               Dr. May FUNG

Committee Members:      Dr. Yangqiu SONG (Supervisor)
                        Dr. Binhang YUAN