Publications

2026

1. The Limits of De-politicizing—and Also of Annotation: A Case Study in Russian Media Outlets’ Social Media Posts, 2016-2024

   Liancheng Gong, Daniel J. Hopkins, and Samuel Wolken

   In International Conference on Web and Social Media (ICWSM) [forthcoming] , 2026

   Bib

   @inproceedings{gong-2026-limits,
     title = {The Limits of De-politicizing—and Also of Annotation: A Case Study in Russian Media Outlets' Social Media Posts, 2016-2024},
     author = {Gong, Liancheng and Hopkins, Daniel J. and Wolken, Samuel},
     booktitle = {International Conference on Web and Social Media (ICWSM) [forthcoming]},
     year = {2026}
   }

2. Motivational Framing in Networked Publics on Indian Social Media: A Case Study of #HindusUnderAttack

   Anmol Panda, Syeda Zainab Akbar, Julia Mendelsohn, Ceren Budak, and Matthew Bui

   In International Conference on Web and Social Media (ICWSM) [forthcoming] , 2026

   Bib

   @inproceedings{panda-2026-motivational,
     title = {Motivational Framing in Networked Publics on Indian Social Media: A Case Study of #HindusUnderAttack},
     author = {Panda, Anmol and Akbar, Syeda Zainab and Mendelsohn, Julia and Budak, Ceren and Bui, Matthew},
     booktitle = {International Conference on Web and Social Media (ICWSM) [forthcoming]},
     year = {2026}
   }

2025

1. When People are Floods: Analyzing Dehumanizing Metaphors in Immigration Discourse with Large Language Models

   Julia Mendelsohn, and Ceren Budak

   In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2025

   Bib HTML PDF Code Poster Slides

   @inproceedings{mendelsohn-budak-2025-people,
     title = {When People are Floods: Analyzing Dehumanizing Metaphors in Immigration Discourse with Large Language Models},
     author = {Mendelsohn, Julia and Budak, Ceren},
     editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
     booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     month = jul,
     year = {2025},
     address = {Vienna, Austria},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.acl-long.398/},
     doi = {10.18653/v1/2025.acl-long.398},
     pages = {8079--8103},
     isbn = {979-8-89176-251-0},
   }

2. How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment

   Joshua Ashkinaze, Julia Mendelsohn, Li Qiwei, Ceren Budak, and Eric Gilbert

   In Proceedings of the ACM Collective Intelligence Conference , 2025

   Abs Bib HTML PDF

   Exposure to large language model output is rapidly increasing. How will seeing AI-generated ideas affect human ideas? We conducted a dynamic experiment (800+ participants, 40+ countries) where participants viewed creative ideas that were from ChatGPT or prior experimental participants, and then brainstormed their own idea. We varied the number of AI-generated examples (none, low, or high exposure) and if the examples were labeled as “AI” (disclosure). We find that high AI exposure (but not low AI exposure) did not affect the creativity of individual ideas but did increase the average amount and rate of change of collective idea diversity. AI made ideas different, not better. There were no main effects of disclosure. We also found that self-reported creative people were less influenced by knowing an idea was from AI and that participants may knowingly adopt AI ideas when the task is difficult. Our findings suggest that introducing AI ideas may increase collective diversity but not individual creativity.

   @inproceedings{ashkinaze2025ai,
     author = {Ashkinaze, Joshua and Mendelsohn, Julia and Qiwei, Li and Budak, Ceren and Gilbert, Eric},
     title = {How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment},
     year = {2025},
     isbn = {9798400714894},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3715928.3737481},
     doi = {10.1145/3715928.3737481},
     booktitle = {Proceedings of the ACM Collective Intelligence Conference},
     pages = {198–213},
     series = {CI '25},
   }

3. What’s in a Prompt?: A Large-Scale Experiment to Assess the Impact of Prompt Design on the Compliance and Accuracy of LLM-Generated Text Annotations

   Shubham Atreja, Joshua Ashkinaze, Lingyao Li, Julia Mendelsohn, and Libby Hemphill

   Proceedings of the International AAAI Conference on Web and Social Media, 2025

   Bib HTML PDF

   @article{atreja2025prompt,
     title = {What's in a Prompt?: A Large-Scale Experiment to Assess the Impact of Prompt Design on the Compliance and Accuracy of LLM-Generated Text Annotations},
     volume = {19},
     url = {https://ojs.aaai.org/index.php/ICWSM/article/view/35807},
     doi = {10.1609/icwsm.v19i1.35807},
     number = {1},
     journal = {Proceedings of the International AAAI Conference on Web and Social Media},
     author = {Atreja, Shubham and Ashkinaze, Joshua and Li, Lingyao and Mendelsohn, Julia and Hemphill, Libby},
     year = {2025},
     month = jun,
     pages = {122-145},
   }

4. AI-LieDar : Examine the Trade-off Between Utility and Truthfulness in LLM Agents

   Zhe Su, Xuhui Zhou, Sanketh Rangreji, Anubha Kabra, Julia Mendelsohn, Faeze Brahman, and Maarten Sap

   In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , 2025

   Bib HTML PDF

   @inproceedings{su2025ai,
     title = {{AI}-{L}ie{D}ar : Examine the Trade-off Between Utility and Truthfulness in {LLM} Agents},
     author = {Su, Zhe and Zhou, Xuhui and Rangreji, Sanketh and Kabra, Anubha and Mendelsohn, Julia and Brahman, Faeze and Sap, Maarten},
     editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
     booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
     month = apr,
     year = {2025},
     address = {Albuquerque, New Mexico},
     publisher = {Association for Computational Linguistics},
     pages = {11867--11894},
     isbn = {979-8-89176-189-6},
   }

5. T-VEC: A Telecom-Specific Vectorization Model with Enhanced Semantic Understanding via Deep Triplet Loss Fine-Tuning

   Vignesh Ethiraj, Ashwath David, Sidhanth Menon, Divya Vijay, and Vidhyakshaya Kannan

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track , 2025

   Bib HTML PDF

   @inproceedings{ethiraj2025tvec,
     title = {T-VEC: A Telecom-Specific Vectorization Model with Enhanced Semantic Understanding via Deep Triplet Loss Fine-Tuning},
     author = {Ethiraj, Vignesh and David, Ashwath and Menon, Sidhanth and Vijay, Divya and Kannan, Vidhyakshaya},
     booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track},
     editor = {Potdar, Saloni and Rojas-Barahona, Lina and Montella, Sebastien},
     year = {2025},
     month = nov,
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     pages = {2449--2460},
     doi = {10.18653/v1/2025.emnlp-industry.168},
     isbn = {979-8-89176-333-3},
   }