CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910996490092544 |
|---|---|
| author | Ramakrishnan, Aashish Anantha Ramakrishnan, Aadarsh Anantha Lee, Dongwon |
| author_facet | Ramakrishnan, Aashish Anantha Ramakrishnan, Aadarsh Anantha Lee, Dongwon |
| contents | 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/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11300 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships? Ramakrishnan, Aashish Anantha Ramakrishnan, Aadarsh Anantha Lee, Dongwon Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition I.2.7; I.2.10 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/ |
| title | CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships? |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition I.2.7; I.2.10 |
| url | https://arxiv.org/abs/2502.11300 |