Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.03198 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917187225124864 |
|---|---|
| author | He, Weilei Ju, Feng Fan, Zhiyuan Min, Rui Cheng, Minhao Fung, Yi R. |
| author_facet | He, Weilei Ju, Feng Fan, Zhiyuan Min, Rui Cheng, Minhao Fung, Yi R. |
| contents | Evaluating the instruction-following (IF) capabilities of Multimodal Large Language Models (MLLMs) is essential for rigorously assessing how faithfully model outputs adhere to user-specified intentions. Nevertheless, existing benchmarks for evaluating MLLMs' instruction-following capability primarily focus on verbal instructions in the textual modality. These limitations hinder a thorough analysis of instruction-following capabilities, as they overlook the implicit constraints embedded in the semantically rich visual modality. To address this gap, we introduce VC-IFEval, a new benchmark accompanied by a systematically constructed dataset that evaluates MLLMs' instruction-following ability under multimodal settings. Our benchmark systematically incorporates vision-dependent constraints into instruction design, enabling a more rigorous and fine-grained assessment of how well MLLMs align their outputs with both visual input and textual instructions. Furthermore, by fine-tuning MLLMs on our dataset, we achieve substantial gains in visual instruction-following accuracy and adherence. Through extensive evaluation across representative MLLMs, we provide new insights into the strengths and limitations of current models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03198 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Empowering Reliable Visual-Centric Instruction Following in MLLMs He, Weilei Ju, Feng Fan, Zhiyuan Min, Rui Cheng, Minhao Fung, Yi R. Machine Learning Evaluating the instruction-following (IF) capabilities of Multimodal Large Language Models (MLLMs) is essential for rigorously assessing how faithfully model outputs adhere to user-specified intentions. Nevertheless, existing benchmarks for evaluating MLLMs' instruction-following capability primarily focus on verbal instructions in the textual modality. These limitations hinder a thorough analysis of instruction-following capabilities, as they overlook the implicit constraints embedded in the semantically rich visual modality. To address this gap, we introduce VC-IFEval, a new benchmark accompanied by a systematically constructed dataset that evaluates MLLMs' instruction-following ability under multimodal settings. Our benchmark systematically incorporates vision-dependent constraints into instruction design, enabling a more rigorous and fine-grained assessment of how well MLLMs align their outputs with both visual input and textual instructions. Furthermore, by fine-tuning MLLMs on our dataset, we achieve substantial gains in visual instruction-following accuracy and adherence. Through extensive evaluation across representative MLLMs, we provide new insights into the strengths and limitations of current models. |
| title | Empowering Reliable Visual-Centric Instruction Following in MLLMs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.03198 |