{"ID":2869303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.14886","arxiv_id":"2509.14886","title":"A Multi-To-One Interview Paradigm for Efficient MLLM Evaluation","abstract":"The rapid progress of Multi-Modal Large Language Models (MLLMs) has spurred the creation of numerous benchmarks. However, conventional full-coverage Question-Answering evaluations suffer from high redundancy and low efficiency. Inspired by human interview processes, we propose a multi-to-one interview paradigm for efficient MLLM evaluation. Our framework consists of (i) a two-stage interview strategy with pre-interview and formal interview phases, (ii) dynamic adjustment of interviewer weights to ensure fairness, and (iii) an adaptive mechanism for question difficulty-level chosen. Experiments on different benchmarks show that the proposed paradigm achieves significantly higher correlation with full-coverage results than random sampling, with improvements of up to 17.6% in PLCC and 16.7% in SRCC, while reducing the number of required questions. These findings demonstrate that the proposed paradigm provides a reliable and efficient alternative for large-scale MLLM benchmarking.","short_abstract":"The rapid progress of Multi-Modal Large Language Models (MLLMs) has spurred the creation of numerous benchmarks. However, conventional full-coverage Question-Answering evaluations suffer from high redundancy and low efficiency. Inspired by human interview processes, we propose a multi-to-one interview paradigm for effi...","url_abs":"https://arxiv.org/abs/2509.14886","url_pdf":"https://arxiv.org/pdf/2509.14886v1","authors":"[\"Ye Shen\",\"Junying Wang\",\"Farong Wen\",\"Yijin Guo\",\"Qi Jia\",\"Zicheng Zhang\",\"Guangtao Zhai\"]","published":"2025-09-18T12:07:40Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}