A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Haorui, Ruiz-Dolz, Ramon, Yi, Qiufeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911412690878464
author Yu, Haorui
Ruiz-Dolz, Ramon
Yi, Qiufeng
author_facet Yu, Haorui
Ruiz-Dolz, Ramon
Yi, Qiufeng
contents This study aims to test and evaluate the capabilities and characteristics of current mainstream Visual Language Models (VLMs) in generating critiques for traditional Chinese painting. To achieve this, we first developed a quantitative framework for Chinese painting critique. This framework was constructed by extracting multi-dimensional evaluative features covering evaluative stance, feature focus, and commentary quality from human expert critiques using a zero-shot classification model. Based on these features, several representative critic personas were defined and quantified. This framework was then employed to evaluate selected VLMs such as Llama, Qwen, or Gemini. The experimental design involved persona-guided prompting to assess the VLM's ability to generate critiques from diverse perspectives. Our findings reveal the current performance levels, strengths, and areas for improvement of VLMs in the domain of art critique, offering insights into their potential and limitations in complex semantic understanding and content generation tasks. The code used for our experiments can be publicly accessed at: https://github.com/yha9806/VULCA-EMNLP2025.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks
Yu, Haorui
Ruiz-Dolz, Ramon
Yi, Qiufeng
Computation and Language
This study aims to test and evaluate the capabilities and characteristics of current mainstream Visual Language Models (VLMs) in generating critiques for traditional Chinese painting. To achieve this, we first developed a quantitative framework for Chinese painting critique. This framework was constructed by extracting multi-dimensional evaluative features covering evaluative stance, feature focus, and commentary quality from human expert critiques using a zero-shot classification model. Based on these features, several representative critic personas were defined and quantified. This framework was then employed to evaluate selected VLMs such as Llama, Qwen, or Gemini. The experimental design involved persona-guided prompting to assess the VLM's ability to generate critiques from diverse perspectives. Our findings reveal the current performance levels, strengths, and areas for improvement of VLMs in the domain of art critique, offering insights into their potential and limitations in complex semantic understanding and content generation tasks. The code used for our experiments can be publicly accessed at: https://github.com/yha9806/VULCA-EMNLP2025.
title A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks
topic Computation and Language
url https://arxiv.org/abs/2509.23208