My research focuses on making machine learning more useful, more
interpretable, and able to learn and interact from humans. This helps
users sift through decades of documents; discover when individuals lie,
reframe, or change the topic in a conversation; or to compete against
humans in games that are based in natural language.
Srikanth, Neha Pundlik, Rupak Sarkar, Mane, Heran Y., Aparicio, Elizabeth M., Nguyen, Quynh C., Rachel Rudinger, and Jordan Boyd-Graber. Large Language Models Help Humans Verify Truthfulness---Except When They Are Convincingly Wrong. North American Association for Computational Linguistics, 2024. [Bibtex]
@inproceedings{Pundlik:Sarkar:Y.:M.:C.:Rudinger:Boyd-Graber-2024,
Title = {Large Language Models Help Humans Verify Truthfulness---Except When They Are Convincingly Wrong},
Author = {Srikanth, Neha Pundlik and Rupak Sarkar and Mane, Heran Y. and Aparicio, Elizabeth M. and Nguyen, Quynh C. and Rachel Rudinger and Jordan Boyd-Graber},
Booktitle = {North American Association for Computational Linguistics},
Year = {2024},
}
Chenglei Si, Navita Goyal, Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, and Jordan Lee Boyd-Graber. Large Language Models Help Humans Verify Truthfulness---Except When They Are Convincingly Wrong. North American Association for Computational Linguistics, 2024. [Bibtex]
@inproceedings{Si:Goyal:Wu:Zhao:Feng:III:Boyd-Graber-2024,
Title = {Large Language Models Help Humans Verify Truthfulness---Except When They Are Convincingly Wrong},
Author = {Chenglei Si and Navita Goyal and Tongshuang Wu and Chen Zhao and Shi Feng and Hal Daum\'{e} {III} and Jordan Lee Boyd-Graber},
Booktitle = {North American Association for Computational Linguistics},
Year = {2024},
}
@inproceedings{Grissom-II:Shoemaker:Goldman:Shi:Stewart:Rytting:Findlater:Boyd-Graber:Li:Grissom-II:Boyd-Graber-2024,
Author = {Alvin {Grissom II} and Jo Shoemaker and Benjamin Goldman and Ruikang Shi and Craig Stewart and C. Anton Rytting and Leah Findlater and Jordan Boyd-Graber},
Location = {Torino, Italy},
Url = {http://umiacs.umd.edu/~jbg//docs/2024_lrec_siminthelp.pdf},
Booktitle = {Linguistic Resources and Evaluation Conference},
Year = {2024},
Title = {Rapidly Piloting Real-time Linguistic Assistance for Simultaneous Interpreters with Untrained Bilingual Surrogates},
}
Quynh C. Nguyen, Elizabeth M. Aparicio, Michelle Jasczynski, Amara Channell Doig, Xiaohe Yue, Heran Mane, Neha Pundlik Srikanth, Francia Ximena Marin Gutierrez, Nataly Delcid, Xin He, and Jordan Boyd-Graber. Randomized Pilot of Rosie, a Health Education Question-and-Answer Chatbot for New Mothers. Journal of Medical Internet Research: Journal of Formative Research, 2024. [Bibtex]
@article{Nguyen:Aparicio:Jasczynski:Doig:Yue:Mane:Srikanth:Gutierrez:Delcid:He:Boyd-Graber-2024,
Title = {Randomized Pilot of Rosie, a Health Education Question-and-Answer Chatbot for New Mothers},
Author = {Quynh C. Nguyen and Elizabeth M. Aparicio and Michelle Jasczynski and Amara Channell Doig and Xiaohe Yue and Heran Mane and Neha Pundlik Srikanth and Francia Ximena Marin Gutierrez and Nataly Delcid and Xin He and Jordan Boyd-Graber},
Journal = {Journal of Medical Internet Research: Journal of Formative Research},
Year = {2024},
}
Zongxia Li, Andrew Mao, Daniel Kofi Stephens, Pranav Goel, Emily Walpole, Juan Francisco Fung, Alden Dima, and Jordan Lee Boyd-Graber. TENOR: Topic Enabled Neural Organization and Recommendation: Evaluating Topic Models in Task Based Settings. European Association for Computational Linguistics, 2024. [Bibtex]
@inproceedings{Li:Mao:Stephens:Goel:Walpole:Fung:Dima:Boyd-Graber-2024,
Title = {TENOR: Topic Enabled Neural Organization and Recommendation: Evaluating Topic Models in Task Based Settings},
Author = {Zongxia Li and Andrew Mao and Daniel Kofi Stephens and Pranav Goel and Emily Walpole and Juan Francisco Fung and Alden Dima and Jordan Lee Boyd-Graber},
Booktitle = {European Association for Computational Linguistics},
Year = {2024},
}
Ishani Mondal, Shwetha S, Anandhavelu Natarajan, Aparna Garimella, Sambaran Bandyopadhyay, and Jordan Lee Boyd-Graber. Presentations by the People, for the People: Harnessing LLMs for Generating Persona-Aware Slides from Documents. European Association for Computational Linguistics, 2024. [Bibtex]
@inproceedings{Mondal:S:Natarajan:Garimella:Bandyopadhyay:Boyd-Graber-2024,
Title = {Presentations by the People, for the People: Harnessing LLMs for Generating Persona-Aware Slides from Documents},
Author = {Ishani Mondal and Shwetha S and Anandhavelu Natarajan and Aparna Garimella and Sambaran Bandyopadhyay and Jordan Lee Boyd-Graber},
Booktitle = {European Association for Computational Linguistics},
Year = {2024},
}
@article{Y.:Amara:Ximena:Michelle:Xiaohe:Pundlik:Sourabh:Abby:Ann:Pragat:Xin:Lee:M.:C.-2023,
Title = {Practical Guidance for the Development of Rosie, a Health Education Question-and-Answer Chatbot for New Mothers},
Author = {Mane, Heran Y. and Channell Doig, Amara and Marin Gutierrez, Francia Ximena and Jasczynski, Michelle and Yue, Xiaohe and Srikanth, Neha Pundlik and Mane, Sourabh and Sun, Abby and Moats, Rachel Ann and Patel, Pragat and He, Xin and Boyd-Graber, Jordan Lee and Aparicio, Elizabeth M. and Nguyen, Quynh C.},
Journal = {Journal of Public Health Management and Practice},
Year = {2023},
Url = {https://journals.lww.com/jphmp/fulltext/2023/09000/practical_guidance_for_the_development_of_rosie,_a.9.aspx},
}
Chenglei Si, Zhe Gan, Zhengyuan Yang, Shuohang Wang, Jianfeng Wang, Jordan Boyd-Graber, and Lijuan Wang. Prompting GPT-3 To Be Reliable. International Conference on Learning Representations, 2023. [Code] [Bibtex]
@inproceedings{Si:Gan:Yang:Wang:Wang:Boyd-Graber:Wang-2023,
Title = {Prompting GPT-3 To Be Reliable},
Author = {Chenglei Si and Zhe Gan and Zhengyuan Yang and Shuohang Wang and Jianfeng Wang and Jordan Boyd-Graber and Lijuan Wang},
Booktitle = {International Conference on Learning Representations},
Year = {2023},
Url = {http://umiacs.umd.edu/~jbg//docs/2023_iclr_reliable.pdf},
}
@article{Si:Shi:Zhao:Zettlemoyer:Boyd-Graber-2023,
Title = {Getting \underline{MoRE} out of \underline{M}ixture \underline{o}f Language Model \underline{R}easoning \underline{E}xperts},
Author = {Chenglei Si and Weijia Shi and Chen Zhao and Luke Zettlemoyer and Jordan Lee Boyd-Graber},
Journal = {Findings of Empirical Methods in Natural Language Processing},
Year = {2023},
Location = {Singapore},
Url = {http://umiacs.umd.edu/~jbg//docs/2023_findings_more.pdf},
}
Accessible Abstract: There are many ways for a computer to answer a question: a general knowledge question, a common sense question, or a math question. Each of these types of questions can be answered by a particular kind of expert. This paper investigates if we can automatically detect what kind of expert is best suited to answer a question and route the question to the correct expert.
@inproceedings{Sung:Hassan:Boyd-Graber-2023,
Title = {Not all Fake News is Written: A Dataset and Analysis of Misleading Video Headlines},
Author = {Yoo Yeon Sung and Naeemul Hassan and Jordan Boyd-Graber},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = {2023},
Location = {Singapore},
Url = {http://umiacs.umd.edu/~jbg//docs/2023_emnlp_videoheadline.pdf},
}
Accessible Abstract: Misinformation online is not all text-based. More information is being consumed in video form, and both social media companies and external monitors need to know when misleading videos are being shared online. We create a new dataset of misleading videos and describe what makes the problem so challenging.
@inproceedings{Schulhoff:Pinto:Khan:Bouchard:Si:Boyd-Graber:Anati:Tagliabue:Kost:Carnahan-2023,
Title = {Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition},
Author = {Sander V Schulhoff and Jeremy Pinto and Anaum Khan and Louis-François Bouchard and Chenglei Si and Jordan Lee Boyd-Graber and Svetlina Anati and Valen Tagliabue and Anson Liu Kost and Christopher R Carnahan},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = {2023},
Location = {Singapore},
Url = {http://umiacs.umd.edu/~jbg//docs/2023_emnlp_hackaprompt.pdf},
}
This paper was selected as the Best Theme Paper at EMNLP 2023 (1 of 4909)
Accessible Abstract: As more AI services online are provided by prompted language models, we need to be aware of the weaknesses and exploits of the models. We present the HackAPrompt competition to help elicit a broad array of exploits that get around large langauge models.
@inproceedings{Han:Carpuat:Boyd-Graber-2023,
Title = {Automatic Explicitation to Bridge the Background Knowledge Gap in Translation and its Evaluation with Multilingual QA},
Author = {HyoJung Han and Marine Carpuat and Jordan Boyd-Graber},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = {2023},
Location = {Singapore},
Url = {http://umiacs.umd.edu/~jbg//docs/2023_emnlp_explicitation.pdf},
}
Accessible Abstract: Sometimes when you a translating from one language to another, a literal translation is not enough. Sometimes to actually understand what is being said, you need additional context. Professional translators know this, and the process that they use to help a listener is called "explicitation" to capturing cultural differences between source and target audiences. We introduce techniques for automatically generating explicitations, motivated by WikiExpl(a dataset collected from Wikipedia and annotate with human translators), and evaluate the explicitation.
@inproceedings{2023-2023,
Author = {Program Chairs' Report on Peer Review at ACL 2023},
Title = {Anna Rogers, Marzena Karpinska, Jordan Boyd-Graber, Naoaki Okazaki},
Journal = {Association for Computational Linguistics},
Year = {2023},
Location = {Toronto},
Url = {http://umiacs.umd.edu/~jbg//docs/2023_acl_peer_review_report.pdf},
}
Benjamin Börschinger, Jordan Boyd-Graber, Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Michelle Chen Huebscher, Wojciech Gajewski, Yannic Kilcher, Rodrigo Nogueira, and Lierni Sestorain Saralegu. Meta Answering for Machine Reading. ArXiv, Preprint. [Preprint] [Bibtex]
@article{B\"orschinger:Boyd-Graber:Buck:Bulian:Ciaramita:Huebscher:Gajewski:Kilcher:Nogueira:Saralegu-Preprint,
Title = {Meta Answering for Machine Reading},
Author = {Benjamin B\"orschinger and Jordan Boyd-Graber and Christian Buck and Jannis Bulian and Massimiliano Ciaramita and Michelle Chen Huebscher and Wojciech Gajewski and Yannic Kilcher and Rodrigo Nogueira and Lierni Sestorain Saralegu},
Journal = {ArXiv},
Year = {Preprint},
Url = {https://arxiv.org/abs/1911.04156},
}
@article{Rodriguez:Feng:Iyyer:He:Boyd-Graber-Preprint,
Title = {Quizbowl: The Case for Incremental Question Answering},
Author = {Pedro Rodriguez and Shi Feng and Mohit Iyyer and He He and Jordan Boyd-Graber},
Journal = {ArXiv},
Year = {Preprint},
Url = {https://arxiv.org/abs/1904.04792},
}