Victor S. Bursztyn

Victor S. Bursztyn

PhD in Natural Language Processing (Northwestern University).

Research Scientist at Adobe Research.

Posts by Collection

portfolio

publications

Thousands of Small, Constant Rallies: A Large-Scale Analysis of Partisan WhatsApp Groups

Published in Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2020

Acceptance rate of 15%.

Recommended citation: Victor S. Bursztyn and Larry Birnbaum. 2019. Thousands of small, constant rallies: a large-scale analysis of partisan WhatsApp groups. In Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM '19). Association for Computing Machinery, New York, NY, USA, 484–488. DOI:https://doi.org/10.1145/3341161.3342905 https://dl.acm.org/doi/abs/10.1145/3341161.3342905

How Brazilian Congressmen Connect: Homophily and Cohesion in Voting and Donation Networks

Published in Journal of Complex Networks (Oxford University Press), 2020

Recommended citation: Victor S. Bursztyn, Marcelo G. Nunes, and Daniel R. Figueiredo. 2020. How Brazilian Congressmen Connect: Homophily and Cohesion in Voting and Donation Networks, Journal of Complex Networks, Volume 8, Issue 1, February 2020, cnaa006, https://doi.org/10.1093/comnet/cnaa006 https://academic.oup.com/comnet/article-abstract/8/1/cnaa006/5770925

Developing a Conversational Recommendation System for Navigating Limited Options

Published in Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, 2021

Acceptance rate of 39%. Presentation publicly available at: https://www.youtube.com/watch?v=97NOZQPrQr4

Recommended citation: Victor S. Bursztyn, Jennifer Healey, Eunyee Koh, Nedim Lipka, and Larry Birnbaum. 2021. Developing a Conversational Recommendation System for Navigating Limited Options. Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, Article 309, 1–6. DOI:https://doi.org/10.1145/3411763.3451596 https://dl.acm.org/doi/abs/10.1145/3411763.3451596

“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems.

Published in Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2021

Acceptance rate of 17.9%. Paper also invited for oral presentation.

Recommended citation: Victor S. Bursztyn, Jennifer Healey, Nedim Lipka, Eunyee Koh, Doug Downey, and Larry Birnbaum. 2021. “It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1913–1918, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. https://aclanthology.org/2021.emnlp-main.145/

Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections.

Published in NeurIPS Workshop on Machine Learning for Creativity and Design, 2021

A more comprehensive version of the methods in this paper has been submitted as a patent application.

Recommended citation: Victor S. Bursztyn, Jennifer Healey, and Vishwa Vinay. 2021. Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections. In the 2021 NeurIPS Workshop on Machine Learning for Creativity and Design. https://neuripscreativityworkshop.github.io/2021/accepted/ncw_104.pdf

Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models.

Published in Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

Accepted at EMNLP 2022 Findings.

Recommended citation: Victor S. Bursztyn, David Demeter, Doug Downey, and Larry Birnbaum. 2022. Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1676–1686, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. https://aclanthology.org/2022.findings-emnlp.121/

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search.

Published in Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024), 2023

Accepted at ICLR 2024.

Recommended citation: Yuchen Zhuang, Xiang Chen, Tong Yu, Saayan Mitra, Victor S. Bursztyn, Ryan A. Rossi, Somdeb Sarkhel, and Chao Zhang. "ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search." In The Twelfth International Conference on Learning Representations. https://openreview.net/pdf?id=B6pQxqUcT8

RaDA: Retrieval-augmented Web Agent Planning with LLMs.

Published in Findings of the Association for Computational Linguistics: ACL 2024, 2024

Accepted at ACL 2024 Findings.

Recommended citation: Minsoo Kim, Victor S. Bursztyn, Eunyee Koh, Shunan Guo, and Seung-won Hwang. 2024. RaDA: Retrieval-augmented Web Agent Planning with LLMs. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13511–13525, Bangkok, Thailand. Association for Computational Linguistics. https://aclanthology.org/2024.findings-acl.802/

How Aligned are Human Chart Takeaways and LLM Predictions? A Case Study on Bar Charts with Varying Layouts.

Published in IEEE VIS 2024, 2024

Accepted at IEEE VIS 2024, published at IEEE Transactions on Visualization and Computer Graphics.

Recommended citation: Huichen Will Wang, Jane Hoffswell, Sao Myat Thazin Thane, Victor S. Bursztyn and Cindy Xiong Bearfield, "How Aligned are Human Chart Takeaways and LLM Predictions? A Case Study on Bar Charts with Varying Layouts," in IEEE Transactions on Visualization and Computer Graphics, vol. 31, no. 1, pp. 536-546, Jan. 2025, DOI: 10.1109/TVCG.2024.3456378. https://ieeexplore.ieee.org/abstract/document/10681139

Representing Charts as Text for Language Models: An In-Depth Study of Question Answering for Bar Charts.

Published in IEEE VIS 2024, 2024

Accepted at IEEE VIS 2024, published at IEEE Transactions on Visualization and Computer Graphics.

Recommended citation: Victor S. Bursztyn, Jane Hoffswell, Eunyee Koh, and Shunan Guo, "HRepresenting Charts as Text for Language Models: An In-Depth Study of Question Answering for Bar Charts," 2024 IEEE Visualization and Visual Analytics (VIS), St. Pete Beach, FL, USA, 2024, pp. 266-270, doi: 10.1109/VIS55277.2024.00061. https://ieeexplore.ieee.org/abstract/document/10771151

“The Data Says Otherwise” — Towards Automated Fact-checking and Communication of Data Claims.

Published in Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (UIST '24), 2024

Accepted at UIST 2024.

Recommended citation: Yu Fu, Shunan Guo, Jane Hoffswell, Victor S. Bursztyn, Ryan Rossi, and John Stasko. 2024. "The Data Says Otherwise" — Towards Automated Fact-checking and Communication of Data Claims. In Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (UIST '24). Association for Computing Machinery, New York, NY, USA, Article 134, 1–20. https://doi.org/10.1145/3654777.3676359 https://dl.acm.org/doi/abs/10.1145/3654777.3676359

Data Pictorial: Deconstructing Raster Images for Data-Aware Animated Vector Posters.

Published in Adjunct Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (UIST Adjunct '24), 2024

Accepted at UIST 2024.

Recommended citation: Tongyu Zhou, Gromit Yeuk-Yin Chan, Shunan Guo, Jane Hoffswell, Chang Xiao, Victor S. Bursztyn, and Eunyee Koh. 2024. Data Pictorial: Deconstructing Raster Images for Data-Aware Animated Vector Posters. In Adjunct Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (UIST Adjunct '24). Association for Computing Machinery, New York, NY, USA, Article 98, 1–3. https://doi.org/10.1145/3672539.3686353 https://dl.acm.org/doi/abs/10.1145/3672539.3686353

A Flash in the Pan: Better Prompting Strategies to Deploy Out-of-the-Box LLMs as Conversational Recommendation Systems.

Published in Proceedings of the 31st International Conference on Computational Linguistics, 2025

Accepted at COLING 2025.

Recommended citation: Gustavo Adolpho Lucas de Carvalho, Simon Benigeri, Jennifer Healey, Victor S. Bursztyn, David Demeter, and Lawrence Birnbaum. 2025. A Flash in the Pan: Better Prompting Strategies to Deploy Out-of-the-Box LLMs as Conversational Recommendation Systems. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8385–8398, Abu Dhabi, UAE. Association for Computational Linguistics. https://aclanthology.org/2025.coling-main.561/

Comprehensive Sketching: Exploring Infographic Design Alternatives in Parallel.

Published in Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA '25), 2025

Accepted at CHI LBW.

Recommended citation: Xinyu Shi, Shunan Guo, Jane Hoffswell, Gromit Yeuk-Yin Chan, Victor S. Bursztyn, Jian Zhao, and Eunyee Koh. 2025. Comprehensive Sketching: Exploring Infographic Design Alternatives in Parallel. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA '25). Association for Computing Machinery, New York, NY, USA, Article 145, 1–8. https://doi.org/10.1145/3706599.3720182 https://dl.acm.org/doi/abs/10.1145/3706599.3720182

A Case Study of Human-Authored versus Automatic Dashboard Summaries.

Published in Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA '25), 2025

Accepted at CHI LBW.

Recommended citation: Jane Hoffswell, Victor S. Bursztyn, Shunan Guo, and Eunyee Koh. 2025. A Case Study of Human-Authored versus Automatic Dashboard Summaries. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA '25). Association for Computing Machinery, New York, NY, USA, Article 40, 1–7. https://doi.org/10.1145/3706599.3720155 https://dl.acm.org/doi/abs/10.1145/3706599.3720155

Doc-React: Multi-page Heterogeneous Document Question-Answering.

Published in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025

Accepted at ACL 2025.

Recommended citation: Junda Wu, Yu Xia, Tong Yu, Xiang Chen, Sai Sree Harsha, Akash V Maharaj, Ruiyi Zhang, Victor S. Bursztyn, Sungchul Kim, Ryan A. Rossi, Julian McAuley, Yunyao Li, and Ritwik Sinha. 2025. Doc-React: Multi-page Heterogeneous Document Question-answering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 67–78, Vienna, Austria. Association for Computational Linguistics. https://aclanthology.org/2025.acl-short.6/

SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps.

Published in Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Accepted at EMNLP 2025 Findings.

Recommended citation: Neha Srikanth, Victor S. Bursztyn, Puneet Mathur, and Ani Nenkova. 2025. SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 1533–1559, Suzhou, China. Association for Computational Linguistics. https://aclanthology.org/2025.findings-emnlp.81/

Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey.

Published in Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Accepted at EMNLP 2025.

Recommended citation: Mehrab Tanjim, Yeonjun In, Xiang Chen, Victor S. Bursztyn, Ryan A. Rossi, Sungchul Kim, Guang-Jie Ren, Vaishnavi Muppala, Shun Jiang, Yongsung Kim, and Chanyoung Park. 2025. Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 9548–9561, Suzhou, China. Association for Computational Linguistics. https://aclanthology.org/2025.emnlp-main.482/

talks

teaching

Recommending Features for Content Planning Based on Advertiser Polling and Historical Audience Measurements.

U.S. Patent No. 10,448,120. Washington, DC: U.S. Patent and Trademark Office., 2019

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Victor S. Bursztyn, Jonas Furtado Dias, André de Almeida Maximo, Adriana Bechara Prado, and Rodrigo Dias Arruda Senra. 2019. Recommending Features for Content Planning Based on Advertiser Polling and Historical Audience Measurements. U.S. Patent No. 10,448,120. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US10448120B1/en

Methods and Apparatus for a Semantic Multi-Database Data Lake.

U.S. Patent No. 10,901,973. Washington, DC: U.S. Patent and Trademark Office., 2021

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Rodrigo Dias Arruda Senra, Karin Breitman, Adriana Bechara Prado, and Victor S. Bursztyn. 2021. Methods and Apparatus for a Semantic Multi-Database Data Lake. U.S. Patent No. 10,901,973. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US10901973B1/en

Relevance Decay for Time-based Evaluation of Machine Learning Applications.

U.S. Patent No. 10,885,464. Washington, DC: U.S. Patent and Trademark Office., 2021

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Diego Salomone Bruno, Victor S. Bursztyn, Percy Enrique Rivera Salas, and Tiago Salviano Calmon. 2021. Relevance Decay for Time-based Evaluation of Machine Learning Applications. U.S. Patent No. 10,885,464. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US10885464B1/en

Method, Medium, and System for Recommending Compositions of Product Features Using Regression Trees.

U.S. Patent No. 11,030,667. Washington, DC: U.S. Patent and Trademark Office., 2021

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Adriana Bechara Prado, Victor S. Bursztyn, Jonas Furtado Dias, André de Almeida Maximo, and Angelo Ernani Maia Ciarlini. 2021. Method, Medium, and System for Recommending Compositions of Product Features Using Regression Trees. U.S. Patent No. 11,030,667. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US11030667B1/en

Using generative artificial intelligence to evaluate fine-tuned language models.

U.S. Patent No. 18/485,204. Washington, DC: U.S. Patent and Trademark Office., 2024

Patent applied while at Adobe Research.

Recommended citation: Victor S. Bursztyn, Xiang Chen, Vaishnavi MUPPALA, Uttaran BHATTACHARYA, Tong Yu, Saayan Mitra, Ryan Rossi, Manas Garg, Kenneth George RUSSELL, Eunyee Koh, Alexandru Ionut Hodorogea. 2025. Using generative artificial intelligence to evaluate fine-tuned language models. U.S. Patent No. 18/485,204. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20250124235A1/en

Generating natural language model insights for data charts using light language models distilled from large language models.

U.S. Patent No. 18/338,033. Washington, DC: U.S. Patent and Trademark Office., 2024

Patent applied while at Adobe Research.

Recommended citation: Victor S. Bursztyn, Wei Zhang, Prithvi Bhutani, Eunyee Koh, and Abhisek Trivedi. 2024. Generating natural language model insights for data charts using light language models distilled from large language models. U.S. Patent No. 18/338,033. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20240320421A1/en

In-context and semantic-aware ensemble model for document retrieval.

U.S. Patent No. 12,380,120. Washington, DC: U.S. Patent and Trademark Office., 2025

Patent applied while at Adobe Research.

Recommended citation: Tong Yu, Xiang Chen, Victor S. Bursztyn, Uttaran BHATTACHARYA, Eunyee Koh, Saayan Mitra, Alexandru Ionut Hodorogea, Kenneth Russell, Saurabh Tripathy, and Manas Garg. 2025. In-context and semantic-aware ensemble model for document retrieval. U.S. Patent No. 12,380,120. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20250147973A1/en

Generating and executing action plans involving software tools via a large language model.

U.S. Patent No. 18/589,065. Washington, DC: U.S. Patent and Trademark Office., 2025

Patent applied while at Adobe Research.

Recommended citation: Yuchen Zhuang, Xiang Chen, Victor S. Bursztyn, Tong Yu, Somdeb Sarkhel, Saayan Mitra, and Ryan A Rossi. 2025. Generating and executing action plans involving software tools via a large language model. U.S. Patent No. 18/589,065. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20250272544A1/en

Reducing hallucinations for generative text responses using a machine learning prompt ensemble.

U.S. Patent No. 18/612,566. Washington, DC: U.S. Patent and Trademark Office., 2025

Patent applied while at Adobe Research.

Recommended citation: Tong Yu, Xiang Chen, Victor S. Bursztyn, Sungchul Kim, Ryan A Rossi, Ruiyi Zhang, and Rui Wang. 2025. Reducing hallucinations for generative text responses using a machine learning prompt ensemble. U.S. Patent No. 18/612,566. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US11914635B2/en