Progressive Multimodal Reasoning via Active Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915071256428544 |
|---|---|
| author | Dong, Guanting Zhang, Chenghao Deng, Mengjie Zhu, Yutao Dou, Zhicheng Wen, Ji-Rong |
| author_facet | Dong, Guanting Zhang, Chenghao Deng, Mengjie Zhu, Yutao Dou, Zhicheng Wen, Ji-Rong |
| contents | Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In this paper, we propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs through Active Retrieval (AR) and Monte Carlo Tree Search (MCTS). Our approach begins with the development of a unified retrieval module that retrieves key supporting insights for solving complex reasoning problems from a hybrid-modal retrieval corpus. To bridge the gap in automated multimodal reasoning verification, we employ the MCTS algorithm combined with an active retrieval mechanism, which enables the automatic generation of step-wise annotations. This strategy dynamically retrieves key insights for each reasoning step, moving beyond traditional beam search sampling to improve the diversity and reliability of the reasoning space. Additionally, we introduce a process reward model that aligns progressively to support the automatic verification of multimodal reasoning tasks. Experimental results across three complex multimodal reasoning benchmarks confirm the effectiveness of the AR-MCTS framework in enhancing the performance of various multimodal models. Further analysis demonstrates that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14835 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Progressive Multimodal Reasoning via Active Retrieval Dong, Guanting Zhang, Chenghao Deng, Mengjie Zhu, Yutao Dou, Zhicheng Wen, Ji-Rong Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Information Retrieval Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In this paper, we propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs through Active Retrieval (AR) and Monte Carlo Tree Search (MCTS). Our approach begins with the development of a unified retrieval module that retrieves key supporting insights for solving complex reasoning problems from a hybrid-modal retrieval corpus. To bridge the gap in automated multimodal reasoning verification, we employ the MCTS algorithm combined with an active retrieval mechanism, which enables the automatic generation of step-wise annotations. This strategy dynamically retrieves key insights for each reasoning step, moving beyond traditional beam search sampling to improve the diversity and reliability of the reasoning space. Additionally, we introduce a process reward model that aligns progressively to support the automatic verification of multimodal reasoning tasks. Experimental results across three complex multimodal reasoning benchmarks confirm the effectiveness of the AR-MCTS framework in enhancing the performance of various multimodal models. Further analysis demonstrates that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning. |
| title | Progressive Multimodal Reasoning via Active Retrieval |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Information Retrieval |
| url | https://arxiv.org/abs/2412.14835 |