Sambaran Bandyopadhyay
Sambaran Bandyopadhyay has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Aparna Garimella
Adobe Research India
3 shared publications Anandhavelu Natarajan
Adobe Research
2 shared publicationsHimanshu Maheshwari
Adobe Research
2 shared publications- Anandhavelu Natarajan
Adobe Research
1 shared publication Ananth Muppidi
Adobe Research
1 shared publication- Apoorv Saxena
Adobe Research India
1 shared publication
Latest Publications
- Open Access
Taming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedback
The generation of presentation slides automatically is an important problem in the era of generative AI. This paper focuses on evaluating multimodal content in presentation slides that can effectively summarize a document and convey concepts to a broad audience. We introduce a benchmark dataset, RefSlides, consisting of human-made high-quality presentations that span various topics. Next, we propose a set of metrics to characterize different intrinsic properties of the content of a presentation and present REFLEX, an evaluation approach that generates scores and actionable feedback for these metrics. We achieve this by generating negative presentation samples with different degrees of metric-specific perturbations and use them to fine-tune LLMs. This reference-free evaluation technique does not require ground truth presentations during inference. Our extensive automated and human experiments demonstrate that our evaluation approach outperforms classical heuristic-based and state-of-the-art large language model-based evaluations in generating scores and explanations.
Open AccessTaming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedback
The generation of presentation slides automatically is an important problem in the era of generative AI. This paper focuses on evaluating multimodal content in presentation slides that can effectively summarize a document and convey concepts to a broad audience. We introduce a benchmark dataset, RefSlides, consisting of human-made high-quality presentations that span various topics. Next, we propose a set of metrics to characterize different intrinsic properties of the content of a presentation and present REFLEX, an evaluation approach that generates scores and actionable feedback for these metrics. We achieve this by generating negative presentation samples with different degrees of metric-specific perturbations and use them to fine-tune LLMs. This reference-free evaluation technique does not require ground truth presentations during inference. Our extensive automated and human experiments demonstrate that our evaluation approach outperforms classical heuristic-based and state-of-the-art large language model-based evaluations in generating scores and explanations.
- Open Access
Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution
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.
Open AccessPresentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution
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.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2664-2684
Presentations by the Humans and For the Humans: Harnessing LLMs for Generating Persona-Aware Slides from Documents
Ishani Mondal, Shwetha S, Anandhavelu Natarajan, Aparna Garimella, Sambaran Bandyopadhyay, Jordan Boyd-Graber. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2664-2684
Open AccessPresentations by the Humans and For the Humans: Harnessing LLMs for Generating Persona-Aware Slides from Documents
Ishani Mondal, Shwetha S, Anandhavelu Natarajan, Aparna Garimella, Sambaran Bandyopadhyay, Jordan Boyd-Graber. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 222-229
Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach
Sambaran Bandyopadhyay, Himanshu Maheshwari, Anandhavelu Natarajan, Apoorv Saxena. Proceedings of the 17th International Natural Language Generation Conference. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 222-229
Open AccessEnhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach
Sambaran Bandyopadhyay, Himanshu Maheshwari, Anandhavelu Natarajan, Apoorv Saxena. Proceedings of the 17th International Natural Language Generation Conference. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 22206-22216
Is This a Bad Table? A Closer Look at the Evaluation of Table Generation from Text
Pritika Ramu, Aparna Garimella, Sambaran Bandyopadhyay. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 22206-22216
Open AccessIs This a Bad Table? A Closer Look at the Evaluation of Table Generation from Text
Pritika Ramu, Aparna Garimella, Sambaran Bandyopadhyay. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.