Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2410.14668 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929735058063360 |
|---|---|
| author | Zhou, Xiongtao He, Jie Chen, Lanyu Li, Jingyu Chen, Haojing Gutiérrez-Basulto, Víctor Pan, Jeff Z. Chen, Hanjie |
| author_facet | Zhou, Xiongtao He, Jie Chen, Lanyu Li, Jingyu Chen, Haojing Gutiérrez-Basulto, Víctor Pan, Jeff Z. Chen, Hanjie |
| contents | Multimodal Chain of Thought (MCoT) is a popular prompting strategy for improving the performance of multimodal large language models (MLLMs) across a range of complex reasoning tasks. Despite its popularity, there is a notable absence of automated methods for evaluating the quality of reasoning steps in MCoT. To address this gap, we propose Multimodal Chain-of-Thought Evaluation (MiCEval), a framework designed to assess the correctness of reasoning chains by evaluating the quality of both the description and each reasoning step. The evaluation of the description component focuses on the accuracy of the image descriptions, while the reasoning step evaluates the quality of each step as it is conditionally generated based on the preceding steps. MiCEval is built upon a fine-grained dataset with annotations that rate each step according to correctness, relevance, and informativeness. Extensive experiments on four state-of-the-art MLLMs show that step-wise evaluations using MiCEval align more closely with human judgments compared to existing methods based on cosine similarity or fine-tuning approaches. MiCEval datasets and code can be found in https://github.com/alenai97/MiCEval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14668 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MiCEval: Unveiling Multimodal Chain of Thought's Quality via Image Description and Reasoning Steps Zhou, Xiongtao He, Jie Chen, Lanyu Li, Jingyu Chen, Haojing Gutiérrez-Basulto, Víctor Pan, Jeff Z. Chen, Hanjie Computation and Language Multimodal Chain of Thought (MCoT) is a popular prompting strategy for improving the performance of multimodal large language models (MLLMs) across a range of complex reasoning tasks. Despite its popularity, there is a notable absence of automated methods for evaluating the quality of reasoning steps in MCoT. To address this gap, we propose Multimodal Chain-of-Thought Evaluation (MiCEval), a framework designed to assess the correctness of reasoning chains by evaluating the quality of both the description and each reasoning step. The evaluation of the description component focuses on the accuracy of the image descriptions, while the reasoning step evaluates the quality of each step as it is conditionally generated based on the preceding steps. MiCEval is built upon a fine-grained dataset with annotations that rate each step according to correctness, relevance, and informativeness. Extensive experiments on four state-of-the-art MLLMs show that step-wise evaluations using MiCEval align more closely with human judgments compared to existing methods based on cosine similarity or fine-tuning approaches. MiCEval datasets and code can be found in https://github.com/alenai97/MiCEval. |
| title | MiCEval: Unveiling Multimodal Chain of Thought's Quality via Image Description and Reasoning Steps |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.14668 |