MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation

TL;DR

This paper introduces MMRC, a comprehensive benchmark for evaluating multimodal large language models in real-world conversations, highlighting their limitations and proposing a note-taking strategy to improve performance.

Contribution

The paper presents MMRC, a large-scale real-world conversation benchmark, and proposes a note-taking method to enhance MLLMs' conversational abilities.

Findings

MLLMs show accuracy drops in real-world scenarios.

Identified failure patterns include memory degradation and error propagation.

Note-taking strategy improves model performance.

Abstract

Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, and reason in sustained interactions within real-world scenarios remain underexplored. This paper introduces MMRC, a Multi-Modal Real-world Conversation benchmark for evaluating six core open-ended abilities of MLLMs: information extraction, multi-turn reasoning, information update, image management, memory recall, and answer refusal. With data collected from real-world scenarios, MMRC comprises 5,120 conversations and 28,720 corresponding manually labeled questions, posing a significant challenge to existing MLLMs. Evaluations on 20 MLLMs in MMRC indicate an accuracy drop during open-ended interactions. We identify four common failure patterns: long-term memory degradation, inadequacies in updating factual knowledge, accumulated assumption of error propagation, and reluctance to say no. To mitigate these issues, we propose a simple yet effective NOTE-TAKING strategy, which can record key information from the conversation and remind the model during its responses, enhancing conversational capabilities. Experiments across six MLLMs demonstrate significant performance improvements.