Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation

Autor:	Yang, Jheng-Hong, Lin, Jimmy
Rok vydání:	2024
Předmět:	Computer Science - Information Retrieval Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Multimedia
Druh dokumentu:	Working Paper
Popis:	Vision--Language Models (VLMs) have demonstrated success across diverse applications, yet their potential to assist in relevance judgments remains uncertain. This paper assesses the relevance estimation capabilities of VLMs, including CLIP, LLaVA, and GPT-4V, within a large-scale \textit{ad hoc} retrieval task tailored for multimedia content creation in a zero-shot fashion. Preliminary experiments reveal the following: (1) Both LLaVA and GPT-4V, encompassing open-source and closed-source visual-instruction-tuned Large Language Models (LLMs), achieve notable Kendall's $\tau \sim 0.4$ when compared to human relevance judgments, surpassing the CLIPScore metric. (2) While CLIPScore is strongly preferred, LLMs are less biased towards CLIP-based retrieval systems. (3) GPT-4V's score distribution aligns more closely with human judgments than other models, achieving a Cohen's $\kappa$ value of around 0.08, which outperforms CLIPScore at approximately -0.096. These findings underscore the potential of LLM-powered VLMs in enhancing relevance judgments. Comment: Accepted by ACM SIGIR 2024 LLM4Eval Workshop: https://llm4eval.github.io/papers
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.01363 Zobrazit plný text záznamu View this record from Arxiv