MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
- URL: http://arxiv.org/abs/2502.09621v1
- Date: Thu, 13 Feb 2025 18:59:46 GMT
- Title: MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
- Authors: Dongzhi Jiang, Renrui Zhang, Ziyu Guo, Yanwei Li, Yu Qi, Xinyan Chen, Liuhui Wang, Jianhan Jin, Claire Guo, Shen Yan, Bo Zhang, Chaoyou Fu, Peng Gao, Hongsheng Li,
- Abstract summary: Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs)
We introduce MME-CoT, a specialized benchmark evaluating the CoT reasoning performance of LMMs.
We conduct an in-depth analysis of state-of-the-art LMMs, uncovering several key insights.
- Score: 63.23935582919081
- License:
- Abstract: Answering questions with Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), yet its impact on Large Multimodal Models (LMMs) still lacks a systematic assessment and in-depth investigation. In this paper, we introduce MME-CoT, a specialized benchmark evaluating the CoT reasoning performance of LMMs, spanning six domains: math, science, OCR, logic, space-time, and general scenes. As the first comprehensive study in this area, we propose a thorough evaluation suite incorporating three novel metrics that assess the reasoning quality, robustness, and efficiency at a fine-grained level. Leveraging curated high-quality data and a unique evaluation strategy, we conduct an in-depth analysis of state-of-the-art LMMs, uncovering several key insights: 1) Models with reflection mechanism demonstrate a superior CoT quality, with Kimi k1.5 outperforming GPT-4o and demonstrating the highest quality results; 2) CoT prompting often degrades LMM performance on perception-heavy tasks, suggesting a potentially harmful overthinking behavior; and 3) Although the CoT quality is high, LMMs with reflection exhibit significant inefficiency in both normal response and self-correction phases. We hope MME-CoT serves as a foundation for advancing multimodal reasoning in LMMs. Project Page: https://mmecot.github.io/
Related papers
- M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation [12.042804590050089]
Multidimensional Multi-Agent Debate (M-MAD) is a systematic LLM-based multi-agent framework for advanced machine translation evaluation.
Our findings demonstrate that M-MAD achieves significant advancements by (1) decoupling MQM criteria into distinct evaluation dimensions for fine-grained assessments.
Comprehensive experiments show that M-MAD not only outperforms all existing LLM-as-a-judge methods but also competes with state-of-the-art reference-based automatic metrics.
arXiv Detail & Related papers (2024-12-28T12:11:28Z) - LLaVA-Critic: Learning to Evaluate Multimodal Models [110.06665155812162]
We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator.
LLaVA-Critic is trained using a high-quality critic instruction-following dataset that incorporates diverse evaluation criteria and scenarios.
arXiv Detail & Related papers (2024-10-03T17:36:33Z) - MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark [77.93283927871758]
This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning benchmark.
MMMU-Pro rigorously assesses multimodal models' true understanding and reasoning capabilities.
arXiv Detail & Related papers (2024-09-04T15:31:26Z) - MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.
We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.
Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
arXiv Detail & Related papers (2024-06-20T03:50:23Z) - LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM [83.98966702271576]
This study aims to investigate the feasibility of imparting Point Cloud Quality Assessment (PCQA) knowledge to large multi-modality models (LMMs)
We transform quality labels into textual descriptions during the fine-tuning phase, enabling LMMs to derive quality rating logits from 2D projections of point clouds.
Our experimental results affirm the effectiveness of our approach, showcasing a novel integration of LMMs into PCQA.
arXiv Detail & Related papers (2024-04-28T14:47:09Z) - 2AFC Prompting of Large Multimodal Models for Image Quality Assessment [38.86162365208038]
Two-alternative forced choice (2AFC) prompting is widely regarded as the most reliable way of collecting human opinions of visual quality.
Global quality score of each image estimated by a particular LMM can be efficiently aggregated using the maximum a posterior estimation.
arXiv Detail & Related papers (2024-02-02T06:05:18Z) - MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities [153.37868034779385]
We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks.
Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes.
arXiv Detail & Related papers (2023-08-04T17:59:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.