Vision Language Models as Values Detectors

TL;DR

This study evaluates how well large language models align with human perception in identifying relevant elements in domestic images, revealing potential for improved social and assistive applications.

Contribution

It provides an empirical comparison of LLMs and humans in detecting relevant image elements, highlighting current limitations and future potential for value detection.

Findings

LLaVA 34B performs best among tested models

Models show low but notable alignment with human judgments

Potential for improved applications with better training and prompting

Abstract

Large Language Models integrating textual and visual inputs have introduced new possibilities for interpreting complex data. Despite their remarkable ability to generate coherent and contextually relevant text based on visual stimuli, the alignment of these models with human perception in identifying relevant elements in images requires further exploration. This paper investigates the alignment between state-of-the-art LLMs and human annotators in detecting elements of relevance within home environment scenarios. We created a set of twelve images depicting various domestic scenarios and enlisted fourteen annotators to identify the key element in each image. We then compared these human responses with outputs from five different LLMs, including GPT-4o and four LLaVA variants. Our findings reveal a varied degree of alignment, with LLaVA 34B showing the highest performance but still scoring low. However, an analysis of the results highlights the models' potential to detect value-laden elements in images, suggesting that with improved training and refined prompts, LLMs could enhance applications in social robotics, assistive technologies, and human-computer interaction by providing deeper insights and more contextually relevant responses.