Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution
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_ | 1866929352132788224 |
|---|---|
| author | Maheshwari, Himanshu Bandyopadhyay, Sambaran Garimella, Aparna Natarajan, Anandhavelu |
| author_facet | Maheshwari, Himanshu Bandyopadhyay, Sambaran Garimella, Aparna Natarajan, Anandhavelu |
| contents | Automatically generating a presentation from the text of a long document is a challenging and useful problem. In contrast to a flat summary, a presentation needs to have a better and non-linear narrative, i.e., the content of a slide can come from different and non-contiguous parts of the given document. However, it is difficult to incorporate such non-linear mapping of content to slides and ensure that the content is faithful to the document. LLMs are prone to hallucination and their performance degrades with the length of the input document. Towards this, we propose a novel graph based solution where we learn a graph from the input document and use a combination of graph neural network and LLM to generate a presentation with attribution of content for each slide. We conduct thorough experiments to show the merit of our approach compared to directly using LLMs for this task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13095 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution Maheshwari, Himanshu Bandyopadhyay, Sambaran Garimella, Aparna Natarajan, Anandhavelu Computation and Language Artificial Intelligence Automatically generating a presentation from the text of a long document is a challenging and useful problem. In contrast to a flat summary, a presentation needs to have a better and non-linear narrative, i.e., the content of a slide can come from different and non-contiguous parts of the given document. However, it is difficult to incorporate such non-linear mapping of content to slides and ensure that the content is faithful to the document. LLMs are prone to hallucination and their performance degrades with the length of the input document. Towards this, we propose a novel graph based solution where we learn a graph from the input document and use a combination of graph neural network and LLM to generate a presentation with attribution of content for each slide. We conduct thorough experiments to show the merit of our approach compared to directly using LLMs for this task. |
| title | Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.13095 |