AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
This work addresses the problem of evaluating hallucinations in MLLMs for researchers and practitioners, offering a more efficient and comprehensive benchmark, though it is incremental as it builds on prior evaluation efforts.
The paper tackles the challenge of hallucinations in Multi-modal Large Language Models (MLLMs) by proposing AMBER, an LLM-free multi-dimensional benchmark for evaluating hallucinations across generative and discriminative tasks, including existence, attribute, and relation types, and it provides a low-cost evaluation pipeline and comprehensive analysis of mainstream MLLMs like GPT-4V.
Despite making significant progress in multi-modal tasks, current Multi-modal Large Language Models (MLLMs) encounter the significant challenge of hallucinations, which may lead to harmful consequences. Therefore, evaluating MLLMs' hallucinations is becoming increasingly important in model improvement and practical application deployment. Previous works are limited in high evaluation costs (e.g., relying on humans or advanced LLMs) and insufficient evaluation dimensions (e.g., types of tasks and hallucinations). In this paper, we propose an LLM-free multi-dimensional benchmark AMBER, which can be used to evaluate both generative task and discriminative task including existence, attribute and relation hallucination. Based on AMBER, we design a low-cost and efficient evaluation pipeline. Additionally, we conduct a comprehensive evaluation and detailed analysis of mainstream MLLMs including GPT-4V(ision), and also give guideline suggestions for mitigating hallucinations. The data and code of AMBER are available at https://github.com/junyangwang0410/AMBER.