ACL Findings2026
Toward A Digital Twin of U.S. Congress
Hayden S. Helm, Tianyi Chen, Harvey McGuinness, Paige Lee, Brandon Duderstadt, Carey E. Priebe
Abstract
In this paper we provide evidence that our virtual model of U.S. congresspersons based on a collection of language models moves towards satisfying the definition of a digital twin. In particular, we introduce and provide high-level descriptions of a daily-updated dataset that contains every Tweet from every U.S. congressperson during their respective terms. We demonstrate that a modern language model equipped with congressperson-specific subsets of this data producing Tweets that are largely indistinguishable from actual Tweets posted by their physical counterparts. We illustrate how generated Tweets can be used to predict roll-call vote behaviors and to quantify the likelihood of congresspersons crossing party lines, thereby assisting stakeholders in allocating resources and potentially impacting real-world legislative dynamics. We conclude with a discussion of the limitations and important extensions of our analysis.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- UPPAM: A Unified Pre-training Architecture for Political Actor Modeling based on Language cites Align Voting Behavior with Public Statements for Legislator Representation Learning
- Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models cites Align Voting Behavior with Public Statements for Legislator Representation Learning
- Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models cites UPPAM: A Unified Pre-training Architecture for Political Actor Modeling based on Language
Builds on7
- Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject StudiesGati V. Aher, Rosa I. Arriaga, Adam Tauman KalaiICML 2023 · 651 citations
- RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question AnsweringZihan Zhang, Meng Fang, Ling ChenACL Findings 2024 · 27 citations
- UPPAM: A Unified Pre-training Architecture for Political Actor Modeling based on LanguageXinyi Mou, Zhongyu Wei, Qi Zhang, Xuanjing HuangACL 2023 · 6 citations
- Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language ModelsHao Li, Ruoyuan Gong, Hao JiangAAAI 2025 · 2 citations
- Align Voting Behavior with Public Statements for Legislator Representation LearningXinyi Mou, Zhongyu Wei, Lei Chen, Shangyi Ning et al.ACL 2021
Related papers
- An Embedding Model for Estimating Legislative Preferences from the Frequency and Sentiment of TweetsGregory Spell, Brian Guay, Sunshine Hillygus, Lawrence CarinEMNLP 2020 · 6 citations
- Helping a Friend or Supporting a Cause? Disentangling Active and Passive Cosponsorship in the U.S. CongressGiuseppe Russo, Christoph Gote, Laurence Brandenberger, Sophia Schlosser et al.ACL 2023 · 1 citation
- Understanding the Language of Political Agreement and Disagreement in Legislative TextsMaryam Davoodi, Eric Waltenburg, Dan GoldwasserACL 2020 · 15 citations
- Analyzing Political Parody in Social MediaAntonis Maronikolakis, Danae Sanchez Villegas, Daniel Preotiuc-Pietro, Nikolaos AletrasACL 2020 · 3 citations
- Continuously Updating Digital Twins using Large Language ModelsHarry Amad, Nicolás Astorga, Mihaela van der SchaarICML 2025
