CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?
This work addresses a gap in evaluating MLLMs for pragmatic and intermodal understanding, which is important for researchers and developers in AI and multimodal systems, though it is incremental as it introduces a new benchmark rather than a novel method.
The authors tackled the problem of evaluating multimodal large language models' (MLLMs) ability to understand coherence relationships in multimodal discourse, finding that even top models like Gemini 1.5 Pro and GPT-4o underperform compared to simple classifier-based baselines on their new benchmark, CORDIAL.
Multimodal Large Language Models (MLLMs) are renowned for their superior instruction-following and reasoning capabilities across diverse problem domains. However, existing benchmarks primarily focus on assessing factual and logical correctness in downstream tasks, with limited emphasis on evaluating MLLMs' ability to interpret pragmatic cues and intermodal relationships. To address this gap, we assess the competency of MLLMs in performing Multimodal Discourse Analysis (MDA) using Coherence Relations. Our benchmark, CORDIAL, encompasses a broad spectrum of Coherence Relations across 3 different discourse domains at varying levels of granularity. Through our experiments on 10+ MLLMs employing different prompting strategies, we show that even top models like Gemini 1.5 Pro and GPT-4o fail to match the performance of simple classifier-based baselines. This study emphasizes the need to move beyond similarity-based metrics and adopt a discourse-driven framework for evaluating MLLMs, providing a more nuanced assessment of their capabilities. The benchmark and code are available at: https://aashish2000.github.io/CORDIAL/