A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912511413977088 |
|---|---|
| author | Soman, Sumit Ranjani, H. G. Roychowdhury, Sujoy Sastry, Venkata Dharma Surya Narayana Jain, Akshat Gangrade, Pranav Khan, Ayaaz |
| author_facet | Soman, Sumit Ranjani, H. G. Roychowdhury, Sujoy Sastry, Venkata Dharma Surya Narayana Jain, Akshat Gangrade, Pranav Khan, Ayaaz |
| contents | Question-Answering (QA) from technical documents often involves questions whose answers are present in figures, such as flowcharts or flow diagrams. Text-based Retrieval Augmented Generation (RAG) systems may fail to answer such questions. We leverage graph representations of flowcharts obtained from Visual large Language Models (VLMs) and incorporate them in a text-based RAG system to show that this approach can enable image retrieval for QA in the telecom domain. We present the end-to-end approach from processing technical documents, classifying image types, building graph representations, and incorporating them with the text embedding pipeline for efficient retrieval. We benchmark the same on a QA dataset created based on proprietary telecom product information documents. Results show that the graph representations obtained using a fine-tuned VLM model have lower edit distance with respect to the ground truth, which illustrate the robustness of these representations for flowchart images. Further, the approach for QA using these representations gives good retrieval performance using text-based embedding models, including a telecom-domain adapted one. Our approach also alleviates the need for a VLM in inference, which is an important cost benefit for deployed QA systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22938 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents Soman, Sumit Ranjani, H. G. Roychowdhury, Sujoy Sastry, Venkata Dharma Surya Narayana Jain, Akshat Gangrade, Pranav Khan, Ayaaz Computation and Language Artificial Intelligence 68T50 I.2.7 Question-Answering (QA) from technical documents often involves questions whose answers are present in figures, such as flowcharts or flow diagrams. Text-based Retrieval Augmented Generation (RAG) systems may fail to answer such questions. We leverage graph representations of flowcharts obtained from Visual large Language Models (VLMs) and incorporate them in a text-based RAG system to show that this approach can enable image retrieval for QA in the telecom domain. We present the end-to-end approach from processing technical documents, classifying image types, building graph representations, and incorporating them with the text embedding pipeline for efficient retrieval. We benchmark the same on a QA dataset created based on proprietary telecom product information documents. Results show that the graph representations obtained using a fine-tuned VLM model have lower edit distance with respect to the ground truth, which illustrate the robustness of these representations for flowchart images. Further, the approach for QA using these representations gives good retrieval performance using text-based embedding models, including a telecom-domain adapted one. Our approach also alleviates the need for a VLM in inference, which is an important cost benefit for deployed QA systems. |
| title | A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents |
| topic | Computation and Language Artificial Intelligence 68T50 I.2.7 |
| url | https://arxiv.org/abs/2507.22938 |