Minds, Machines and Society Group

The Minds, Machine, and Society group is led by Prof. Soroush Vosoughi, an assistant professor of Computer Science at Dartmouth. Underpinning our work is the profound interest in developing computational models of cognition, employing language as a primary conduit. We believe that the creative use of language is a distinguishing cognitive skill that sets humans apart from other animals. At a high level, our research primarily focuses on natural language processing (NLP) and machine learning. Specifically, we delve into the intricacies of large language models (LLMs) such as those exemplified by ChatGPT, in an effort to understand and mitigate their anti-social tendencies like promoting stereotypes, spreading toxicity, and misalignment with human values. To increase their transparency and trustworthiness, we work on developing a range of interpretability methods, breaking down their inherent "black box" nature. Our pursuits also encompass techniques such as reinforcement learning for guiding pre-trained LLMs and grounding them using simulations. We also seek to harness the power of LLMs and classical NLP to create computational tools that offer new perspectives on social systems and issues. Our work encompasses studying phenomena such as political polarization, bias, propaganda, rumors, and hate speech, falling under the umbrella of "computational social science". Our research horizons have recently broadened to include the integration of visual information into language models (i.e., visual-language models), aiming to create a more complex representation of the abundant, rich data that exists and drawing us closer to a deeper understanding of human cognition. Also, our exploration now extends to applying LLMs to the health and bioinformatics sectors, motivated by the intriguing parallels between genomic sequences and language. This venture is a collaborative effort with several other faculty at Dartmouth.

Prof. Vosoughi is a recipient of the Google Research Scholar Award in 2022 and an Amazon Research Award in 2019, and his work has earned several Best Paper awards and nominations, including the Outstanding Paper Award at AAAI 2021. He is a Technical Associate Director at Dartmouth's Center for Precision Health and Artificial Intelligence (CPHAI), a faculty member of the Institute for Security, Technology, and Society (ISTS) and a faculty affiliate of the Quantitative Social Science (QSS) program, the Quantitative Biomedical Sciences (QBS) program, and the Arthur L. Irving Institute for Energy & Society at Dartmouth. Before joining Dartmouth, Prof. Vosoughi was a postdoctoral associate at MIT and a fellow and later an affiliate at the Berkman Klein Center at Harvard University. During his time as a postdoc at MIT, he was the technical director of the "Electome" project. His team of graduate and undergraduate students developed a collection of tools for detecting and categorizing election-related content on Twitter, and they were invited to be an official partner of the Commission on Presidential Debates during the 2016 elections. In addition, Prof. Vosoughi served as a technical advisor to the nonprofit organizations Public Mind (formerly Because Humanity), a nonprofit using AI focused on developing AI systems that foster a healthier online public sphere, and Cortico, a nonprofit that builds systems for a healthier public dialogue, from 2021 to 2023 and 2016 to 2019, respectively. He received his Ph.D., MSc, and BSc from MIT in 2015, 2010, and 2008.

Prof. Vosoughi's research has been supported by a variety of prestigious entities. These include the National Science Foundation (NSF) and the National Institute of Health (NIH), alongside industry grants from renowned corporations like Google and Amazon. Furthermore, he has received funding from nonprofit organizations such as the Institute for Humane Studies and the John Templeton Foundation. His work has also benefited from internal grants at Dartmouth, awarded by the Neukom Institute for Computational Science, the Institute for Security, Technology, and Society (ISTS), the Dartmouth Ethics Institute, and the Arthur L. Irving Institute for Energy & Society.

Recent News

[November, 2024] Website is currently being updated. Stayed Tuned! News is not up-to-date.

[February, 2024] Two papers from our lab have been accepted to ICLR 2024: Training Socially Aligned Language Models in Simulated Human Society and Aligning Relational Learning with Lipschitz Fairness.

[February 28, 2024] Congratulations to MMS Ph.D. candidate Ruibo Liu on the successful defense of his thesis titled "Interpretations Allow for an Easy Cure: Lightweight Investigation and Mitigation of Safety Problems in PLMs". Committee members included Prof. Diyi Yang from Stanford University, Dr. Denny Zhou from Google DeepMind, and Professors Yaoqing Yang, SouYoung Jin, and Soroush Vosoughi (Chair) from Dartmouth.

[January 15, 2024] Congratulations to MMS Ph.D. candidate Weicheng Ma on the successful defense of his thesis titled "Interpretations Allow for an Easy Cure: Lightweight Investigation and Mitigation of Safety Problems in PLMs". Committee members included Prof. Dan Roth from the University of Pennsylvania, Prof. Diyi Yang from Stanford University, Prof. Rolando Solano, Prof. Yaoqing Yang, and Prof. Soroush Vosoughi (Chair) from Dartmouth.

[January 12, 2024] Delighted to see our latest research on "Deciphering Stereotypes in Pre-Trained Language Models," featured in Dartmouth News. Our study unveils key insights into how PLMs encode biases and proposes methods for their mitigation.

[January 4, 2024] Congratulations to MMS Ph.D. candidate Yiren Jian on the successful defense of his thesis titled "Efficient and Effective Learning of Foundational Large Multi-Modal Models". Committee members included Prof. Dan Roth from the University of Pennsylvania, Prof. V.S. Subrahmanian from Northwestern University, Prof. Yaoqing Yang, Prof. SouYoung Jin, and Prof. Soroush Vosoughi (Chair) from Dartmouth.

[December 21, 2023] Psychology Today highlights our study on using AI to help detect mental disorders based on web posts.

[December 12, 2023] Excited to give a talk on Strategies for Enterprises to Avoid Generative AI's Antisocial Tendencies at the 2023 TTI/Vanguard: [next] Conference in Half Moon Bay, CA.

[December 1, 2023] Excited to give a talk on Large Language Models and Persuasive Language at the Irving Institute Faculty Seminar Series.

[November 17, 2023] Excited to participate at the Ivy+ Provost Conference on GenAI at Harvard University.

[November 13-15, 2023] Excited to participate and speak at the invitation only Army Research Office sponsored Workshop on Metacognitive Prediction of AI Behavior at ASU.

[October 26, 2023] Delighted to see our lab's work featured in a Nature article on ethical AI: "How Robots Can Learn to Follow a Moral Code."

[October 13, 2023] Excited to give a talk on "Prosocial Language Models", at the Information Sciences Institute (ISI). University of Southern California (USC).

[October 2023] Congratulations to MMS students Yiren Jian and Chiyu (Henry) Ma for winning a NeurIPS 2023 Scholar Award

[October 7, 2023] We have 2 papers accepted to the EMNLP 2023 main conference and 2 to the findings of EMNLP 2023. Congratulations to the first authors, Weicheng Ma, Xiaobo Guo, and Sean Xie! More information about the papers will be coming out soon!

[September 2023] Our paper on Bootstrapping Vision-Language Learning with Decoupled Language Pre-training has been accepted as a spotlight presentation at NeurIPS 2023. Congratulations to the first author, MMS student Yiren Jian.

[September 26, 2023] Excited to give a talk about Generative AI to the New Hampshire House of Representatives' Committee on Science, Technology and Energy.

[September 19, 2023] Excited to participate in a panel titled "Navigating New Frontiers: Generative AI and Passive Sensing in Mental Health?" at the Digital Mental Health & AI Symposium at Dartmouth.

[September 18, 2023] Our recent work (jointly with Dr. Porkhial and Professor Valentino) on computational modeling of participation bias in social media platforms has been covered by Dartmouth News.

[September 14, 2023] Excited to give a talk on "AI: What It Is and What It Is Not", at the 2023 Maine Digital Government Summit on the ethics, challenges, and promises of generative AI.

[August 2023] Our lab's work is discussed in an MIT Technology Review article about the bias of language models.

[August 16, 2023] The Washington Post covered our study titled Mitigating Political Bias in Language Models through Reinforced Calibration," which received the best paper award at AAAI 2021.

[August 7, 2023] Prof. Vosoughi was quoted in an MIT Technology Review article discussing the political bias of language models.

[August 2, 2023] I am honored to have received a grant from the John Templeton Foundation. This grant will be used to study and foster "intellectual humility" in online public discourse by utilizing large language models.

[Summer 2023] Thrilled to join Dartmouth's Center for Precision Health and Artificial Intelligence (CPHAI) as a Technical Associate Director, working under the leadership of Prof. Saeed Hassanpour.

[July 29, 2023] Checkout our paper on Quantifying participation biases on social media, just out in EPJ Data Science. Congratulations to the first author, Neeti Porphoyal.

[Summer 2023] Students from MMS will be gaining practical experience in top-tier companies this summer. Yiren Jian will be working with the Applied Machine Learning Team at TikTok. Xiaobo Guo is set to work with the People Experience and Technology Central Science (PXTCS) team at Amazon Research. Sean Xie will be contributing to research at Capital One. Finally, Ruibo Liu will be continuing his journey with Google Brain. Congratulations to all.

[July 2023] Delighted to be featured in this insightful article in the Communications of ACM about the potential misuse of chatbots and how technology can aid in detecting content related to chatbots.

[June 27, 2023] Excited to co-present a talk titled Artificial Intelligence: Embracing, with Caution, the Latest Developments with Prof. David Kotz. We look forward to addressing a diverse audience of the general public at the Lyme Library in New Hampshire.

[June 2023] Kudos to our MMS undergraduate researchers, Brian Wang, Samiha Data, and John L. McCambridge! They have been awarded the John G. Kemeny Computing Prizes for Excellence in Innovation & Undergraduate Computing. Additionally, Brian Wang deserves special recognition for securing an honorable mention in the Neukom Outstanding Undergraduate Research in Computational Science. Congratulations on your fantastic achievements!

[June 2023] Congratulations to the graduating MMS seniors! This year, we guided eight senior thesis projects. Remarkably, five of these theses earned honors recognition, and two achieved high honors. Well done!

[June 6, 2023] Excited to participate in a panel titled "Is It Real or Is It AI?" at the 2023 New Hampshire Digital Government Summit on the ethics, challenges, and promises of generative AI.

[May 2023] Our paper on "Improving Syntactic Probing Correctness and Robustness with Control Tasks" has been accepted to ACL 2023. Congratulations to the first author, Weicheng Ma, and the rest of the team!

[May 2023] Our paper on "Sentence Level Inference Attack Against Pre-trained Language Models" has been published in the Proceedings on Privacy Enhancing Technologies (PoPETs 2023). Congratulations to the first author, Kang Gu, and the rest of the team!

[May 2023] Our paper on "Joint Latent Topic Discovery and Expectation Modeling for Financial Markets" has been published in the Advances in Knowledge Discovery and Data Mining (PAKDD 2023). Congratulations to the first author, Lili Wang, and the rest of the team!

[April 28, 2023] Excited to participate in the Neukom Institute Workshop on Computational Formalism at Dartmouth College!

[April 25, 2023] Delighted to present our group's work on "Unsupervised Structural Graph Representation Learning" at the Applied and Computational Mathematics Seminar at Dartmouth College.

[April 16, 2023] Excited to be one of judges for HackDartmouth VIII at Dartmouth College.

[March, 2023] Accepted invitation to serve as a member of the Program Committee for NeurIPS 2023

[Feb 24, 2023] Our collaborative paper on "Evaluating native-like structures of RNA-protein complexes through the deep learning method" published in Nature Communications.

[Feb 23, 2023] Paper on "Joint Latent Topic Discovery and Expectation Modeling for Financial Markets" accepted to PAKDD 2023. Congratulations to the first author, Lili Wang!

[Feb 16, 2023] Featured in an article in the Dartmouth News about the conversation around ChatGPT at Dartmouth.

[Jan 21, 2023] Two papers from our lab's collaboration with Google have been accepted to ICLR 2023: Mind's Eye: Grounded Language Model Reasoning through Simulation and Language Models are Multilingual Chain-of-Thought Reasoners. Congratulations to MMS students Ruibo Liu and Suraj Srivats!

[Jan 2, 2023] Accepted invitation to serve as an Area Chair for ACL 2023, Computational Social Science and Cultural Analytics track

[January 2023] Accepted invitation to serve as a member of the Senior Program Committee for AAAI ICWSM 2023 (January Round)

[January 2023] Accepted invitation to serve on the review committee of ICML 2023

[December 2022] Our lab's recent work has been covered Dartmouth News

[Dec 12, 2022] Invited talk on Prosocial Language Models at the Computational Linguistics Seminar (CLunch), NLP group, University of Pennsylvania.

[Dec 9, 2022] Our paper on estimating energy access using satellite data is out in EPJ Data Science

[Dec 8, 2022] Invited talk on Prosocial Language Models at the AI/ML Cross-Disciplinary Seminar. Dartmouth College.

[Nov 21, 2022] Accepted invitation to serve on the Program Committee for the 2023 International Conference on Computational Social Science (IC2S2)

[Nov 14, 2022] Honored to be involved with the Arthur L. Irving Institute for Energy & Society at Dartmouth College as a faculty affiliate

[Oct 27, 2022] Invited talk at the University of Michigan's School of Information Data Science/Computational Social Science Seminar Series on Prosocial Language Models

[Oct 19, 2022] Invited talk at the Dartmouth Climate and Energy Symposium on Modeling Message Receptivity Using Machine Learning

[Oct 8, 2022] One paper accepted to theFindings of EMNLP 2022. Congratulations to the first author Xiaobo Guo

[Oct 7, 2022] Congratulations to MMS student Yiren Jian for winning a NeurIPS 2022 Scholar Award

[Sep, 2022] Honored to be a Co-Investigator on PI Prof. Saeed Hassanpour's NIH R01 proposal on Advancing Digital Pathology through Novel Machine Learning Methodologies

[Sep 30, 2022] Invited talk at the MIT Center for Constructive Communication on Social NLP

[Sep, 2022] Honored to be awarded a Faculty Research Grant by the Ethics Institute at Dartmouth College to support our work on quantifying participation biases on social media

[Sep 14, 2022] Two papers from our group have been accepted to NeurIPS 2022. Congratulations to the first authors Ruibo Liu and Yiren Jian

[Sep, 2022] Honored to be awarded a Junior Faculty Fellowship by Dartmouth College

[Sep, 2022] Accepted invitation to serve on the Program Committee for the ACM Web Conference (WebConf) 2023, Social Network Analysis and Graph Algorithms Track

[Sep 6, 2022] Accepted invitation to serve as a member of the Senior Program Committee for AAAI ICWSM 2023 (September Round)

[Sep 4, 2022] Accepted invitation to serve on the Program Committee for the ACM Web Conference (WebConf) 2023, Web & Society Track

[Sep 2022] PhD student Weicheng Ma to visit Prof. Heng Ji's group at UIUC for the fall term

[Sep 1, 2022] PhD student Ruibo Liu to intern at Google Brain for the fall term

[August 1, 2022] Accepted invitation to serve on the Program Committee of the AAAI-23 Special Track on AI for Social Impact

[July 2022] Accepted invitation to serve on the Program Committee of W-NUT@COLING 2022

[June 5, 2022] Prof. Vosoughi honored with a Google Research Scholar Award in Natural Language Proceesing for his proposal titled "Culture-Aware Language Models"

[June 2, 2022] Congratulations to MMS Ph.D. student Ruibo Liu for winning the 1st place for the Neukom Prize for Outstanding Graduate Research in Computational Science for 2022

[June 2, 2022] Congratulations to MMS undergraduate student Yakoob Khan for winning the 3rd place for the Neukom Prize for Outstanding Undergraduate Research in Computational Science for 2022

[June, 2022] Serving as the Undergraduate Program Director for the CS department for summer 2022

[May, 2022] Accepted invitation to serve as a member of the Program Committee for NeurIPS 2022

[May, 2022] Accepted invitation to serve as a member of the Senior Program Committee for AAAI ICWSM 2023

[April 7, 2022] Three papers from our group have been accepted to NAACL 2022, one paper accpeted to Findings of the NAACL 2022

[April 2022] PhD student Ruibo Liu to start a summer 2022 internship at Google Brain

[April 2022] PhD student Xiaobo Guo to start a summer 2022 internship at Amazon Research

[April 2022] PhD student Yiren Jian to start a summer 2022 internship at Snap Research, Creative Vision Group

[April 2022] PhD student Yuansheng Xie to start a summer 2022 internship at Capital One, Data Science

[March 18, 2022] Two papers from our group have been accepted to AAAI ICWSM 2022

[Feburary 28, 2022] Our paper, "EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English", has been accepted to The Findings of ACL 2022

[Feburary 3, 2022] Accepted invitation to serve on the program committee of NAACL 2022 workshop on HCI + NLP

[January, 2022] Accepted invitation to serve on the review committee of ICML 2022

[January 21, 2022] Two papers from our group have been accepted to ICLR 2022

[January 20, 2022] An extension of our AAAI 2021 paper that won the best paper award has been published in the Journal of Artificial Intelligence

[December, 2021] Accepted invitation to serve as a member of the Senior Program Committee for AAAI ICWSM 2022, January Cycle

[November 26, 2021] Our paper, titled "Dynamic Structural Role Node Embedding for User Modeling in Evolving Networks" has been published in the ACM Transactions on Information Systems (ACM TOIS)

[October 2021] Accepted invitation to serve on the Program Committee for the ACM Web Conference (WebConf) 2022

[October 2021] Our paper, titled "Feature Selection for Multivariate Time Series via Network Pruning" has been accepted to the ICDM 2021 workshop on Systematic Feature Engineering for Time-Series Data Mining (SFE-TSDM)

[October 6, 2021] Accepted invitation to serve on the Program Committee for IJCAI-ECAI 2022

[September 15, 2021] Our paper, titled "SymptomID: A Framework for Rapid Symptom Identification in Pandemics Using News Reports" has been published in the ACM Transactions on Management Information Systems (ACM TMIS)

[September 5, 2021] Accepted invitation to serve on the Program Committee of AAAI 2022

[September 2021] Serving on the Curriculum Committee of the CS department for 2021-2022

[August 26, 2021] Our paper, titled "GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks" has been accepted to EMNLP 2021

[August 18, 2021] Selected as a finalist for Facebook's research award for Statistics for Improving Insights, Models, and Decisions

[August 16, 2021] Our paper, titled "Using impression data to improve models of online social influence" has been published in the journal Scientific Reports

[August 10, 2021] Two papers have been accepted to accepted to CIKM 2021
[June 2021] Accepted invitation to serve on the Program Committee of the 6th Workshop on Noisy User-Generated Text (W-NUT), co-located with EMNLP 2021

[June 14, 2021] One paper has been published in the journal Data Mining and Knowledge Discovery
[June 11, 2021] Congratulations to MMS undergraduate student Yakoob Khan for winning the John G. Kemeny Computing Prize for Innovation for 2021

[May 27, 2021] Congratulations to MMS Ph.D. student Ruibo Liu for winning the 2nd Neukom Prize for Outstanding Graduate Research in Computational Science for 2021

[May 27, 2021] Congratulations to MMS undergraduate student Yakoob Khan for winning the 2nd Neukom Prize for Outstanding Undergraduate Research in Computational Science for 2021

[May 6, 2021] Two papers have been accepted to ACL 2021

[May 6, 2021] Two papers have been accepted to Findings of ACL

[May 5, 2021] Accepted invitation to serve on the Program Committee of the KDD Workshop on Data-driven Humanitarian Mapping

[April 2021] Two papers at SemEval 2021 (Tasks 1 and 5)

[April 2021] PhD student Ruibo Liu to start a summer 2021 internship at Microsoft Research

[April 2021] Accepted invitation to serve on the Program Committee for EMNLP 2021

[March 10, 2021] Two papers have been accepted to NAACL 2021

[Feburary 4, 2021] Best paper award at AAAI 2021 for our paper on "Mitigating Political Bias in Language Models Through Reinforced Calibration"

[January 25, 2021] Team Big Green, led by Prof. Vosoughi, selected as a finalist in the XPRIZE Pandemic Response Challenge

[January 12, 2021] One paper has been accepted to EACL 2021

[December 22, 2020] One paper has been accepted to CSCW 2021

[December 10, 2020] Prof. Vosoughi is leading a Dartmouth team (team Big Green) to compete against 104 teams from 28 countries in the XPRIZE Pandemic Response Challenge

[December 2020] Accepted invitation to serve on the Review Committee of ACL 2021

[December 2, 2020] Two papers have been accepted to AAAI 2021

[December 2020] Accepted invitation to serve on the Review Committee of CVPR 2021

[November 2020] Accepted invitation to serve on the Review Committee of CSCW 2021

[October 2020] Accepted invitation to serve on the Program Committee of NAACL-HLT 2021

[October 11, 2020] One paper has been accepted to ICPR 2020

[September 2020] Accepted invitation to serve on the Program Committee of AAAI 2021

[September 15, 2020] Two papers accepted to EMNLP 2020

[September 7, 2020] Prof. Vosoughi is serving as the fall 2020 undergraduate program director for the CS department

[August 2020] Accepted invitation to serve on the Review Committee of EACL 2021

[August 5, 2020] One paper has been accepted to ACM ICAIF 2020

[July 16, 2020] One paper has been accepted to CIKM 2020

[July 15, 2020] One paper has been accepted to ICWSM 2021

[May 2020] Accepted invitation to serve on the Review Committee of EMNLP 2020

[May 18, 2020] Prof. Vosoughi and Dr. Neeti Pokhriyal awarded an Irving Institute Seed Grant

[April 2020] Accepted invitation to serve on the Program Committee of the KDD 2020 workshop on Humanitarian Mapping

[March 26, 2020] Prof. Vosoughi honored with an Amazon Research Award

[March 8, 2020] One paper accepted to ICMR 2020

[March 2020] Prof. Vosoughi serving on a National Sciene Foundation (NSF) Computer and Information Science and Engineering (CISE) panel

[March 2020] Accepted invitation to serve on the Program Committee of W-NUT@EMNLP 2020

[February 2020] Accepted invitation to serve on the Review Committee of ICWSM 2020