Pritika Ramu
Research Subjects
Pritika Ramu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Aparna Garimella
Adobe Research India
4 shared publications - Apoorv Saxena
Adobe Research India
3 shared publications Akash Ghosh
Indian Institute of Technology Patna India
2 shared publicationsAparna Garimella
Adobe Research
2 shared publications- Sambaran Bandyopadhyay
Adobe Research
2 shared publications - Sriparna Saha
Indian Institute of Technology, Patna, India
2 shared publications
Latest Publications
- Open Access
Infogen: Generating Complex Statistical Infographics from Documents
Statistical infographics are powerful tools that simplify complex data into visually engaging and easy-to-understand formats. Despite advancements in AI, particularly with LLMs, existing efforts have been limited to generating simple charts, with no prior work addressing the creation of complex infographics from text-heavy documents that demand a deep understanding of the content. We address this gap by introducing the task of generating statistical infographics composed of multiple sub-charts (e.g., line, bar, pie) that are contextually accurate, insightful, and visually aligned. To achieve this, we define infographic metadata that includes its title and textual insights, along with sub-chart-specific details such as their corresponding data and alignment. We also present Infodat, the first benchmark dataset for text-to-infographic metadata generation, where each sample links a document to its metadata. We propose Infogen, a two-stage framework where fine-tuned LLMs first generate metadata, which is then converted into infographic code. Extensive evaluations on Infodat demonstrate that Infogen achieves state-of-the-art performance, outperforming both closed and open-source LLMs in text-to-statistical infographic generation.
Open AccessInfogen: Generating Complex Statistical Infographics from Documents
Statistical infographics are powerful tools that simplify complex data into visually engaging and easy-to-understand formats. Despite advancements in AI, particularly with LLMs, existing efforts have been limited to generating simple charts, with no prior work addressing the creation of complex infographics from text-heavy documents that demand a deep understanding of the content. We address this gap by introducing the task of generating statistical infographics composed of multiple sub-charts (e.g., line, bar, pie) that are contextually accurate, insightful, and visually aligned. To achieve this, we define infographic metadata that includes its title and textual insights, along with sub-chart-specific details such as their corresponding data and alignment. We also present Infodat, the first benchmark dataset for text-to-infographic metadata generation, where each sample links a document to its metadata. We propose Infogen, a two-stage framework where fine-tuned LLMs first generate metadata, which is then converted into infographic code. Extensive evaluations on Infodat demonstrate that Infogen achieves state-of-the-art performance, outperforming both closed and open-source LLMs in text-to-statistical infographic generation.
- Open Access
StyleAdaptedLM: Enhancing Instruction Following Models with Efficient Stylistic Transfer
Adapting LLMs to specific stylistic characteristics, like brand voice or authorial tones, is crucial for enterprise communication but challenging to achieve from corpora which lacks instruction-response formatting without compromising instruction adherence. We introduce StyleAdaptedLM, a framework that efficiently transfers stylistic traits to instruction-following models using Low-Rank Adaptation (LoRA). LoRA adapters are first trained on a base model with diverse unstructured stylistic corpora, then merged with a separate instruction-following model. This enables robust stylistic customization without paired data or sacrificing task performance. Experiments across multiple datasets and models demonstrate improved stylistic consistency while preserving instruction adherence, with human evaluations confirming brand-specific convention uptake. StyleAdaptedLM offers an efficient path for stylistic personalization in LLMs.
Open AccessStyleAdaptedLM: Enhancing Instruction Following Models with Efficient Stylistic Transfer
Adapting LLMs to specific stylistic characteristics, like brand voice or authorial tones, is crucial for enterprise communication but challenging to achieve from corpora which lacks instruction-response formatting without compromising instruction adherence. We introduce StyleAdaptedLM, a framework that efficiently transfers stylistic traits to instruction-following models using Low-Rank Adaptation (LoRA). LoRA adapters are first trained on a base model with diverse unstructured stylistic corpora, then merged with a separate instruction-following model. This enables robust stylistic customization without paired data or sacrificing task performance. Experiments across multiple datasets and models demonstrate improved stylistic consistency while preserving instruction adherence, with human evaluations confirming brand-specific convention uptake. StyleAdaptedLM offers an efficient path for stylistic personalization in LLMs.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 34936-34951
Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents
Akriti Jain, Pritika Ramu, Aparna Garimella, Apoorv Saxena. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 34936-34951
Open AccessDoc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents
Akriti Jain, Pritika Ramu, Aparna Garimella, Apoorv Saxena. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 20552-20570
Infogen: Generating Complex Statistical Infographics from Documents
Akash Ghosh, Aparna Garimella, Pritika Ramu, Sambaran Bandyopadhyay, Sriparna Saha. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 20552-20570
Open AccessInfogen: Generating Complex Statistical Infographics from Documents
Akash Ghosh, Aparna Garimella, Pritika Ramu, Sambaran Bandyopadhyay, Sriparna Saha. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 676-694
Zooming in on Zero-Shot Intent-Guided and Grounded Document Generation using LLMs
Pritika Ramu, Pranshu Gaur, Rishita Emandi, Himanshu Maheshwari, Danish Javed, Aparna Garimella. Proceedings of the 17th International Natural Language Generation Conference. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 676-694
Open AccessZooming in on Zero-Shot Intent-Guided and Grounded Document Generation using LLMs
Pritika Ramu, Pranshu Gaur, Rishita Emandi, Himanshu Maheshwari, Danish Javed, Aparna Garimella. Proceedings of the 17th International Natural Language Generation Conference. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 16696-16717
Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness
Srija Mukhopadhyay, Adnan Qidwai, Aparna Garimella, Pritika Ramu, Vivek Gupta, Dan Roth. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 16696-16717
Open AccessUnraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness
Srija Mukhopadhyay, Adnan Qidwai, Aparna Garimella, Pritika Ramu, Vivek Gupta, Dan Roth. Findings of the Association for Computational Linguistics: EMNLP 2024. 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.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 17790-17806
Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition
Pritika Ramu, Koustava Goswami, Apoorv Saxena, Balaji Vasan Srinivasan. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 17790-17806
Open AccessEnhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition
Pritika Ramu, Koustava Goswami, Apoorv Saxena, Balaji Vasan Srinivasan. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.