Explanipedia

Race-Related Research in Economics and Other Social Sciences Open

Arun Advani, Elliott Ash, David Cai, Imran Rasul · 2025

How does economics compare to other social sciences in its study of issues related to race and ethnicity? We assess this using a corpus of 500,000 academic publications in economics, political science, and sociology. Using an algorithmic a…

A large language model-based approach to quantifying the effects of social determinants in liver transplant decisions Open

Emily Robitschek, Asal Bastani, Savyon Sordean, Mark J. Pletcher, Elliott Ash , et al. · 2025

Race‐related research in economics Open

Arun Advani, Elliott Ash, David Cai · 2025

Issues of racial justice and economic inequalities between racial and ethnic groups have risen to the top of public debate. Economists' ability to contribute to these debates is based on the body of race‐related research. We study the volu…

Evaluating GPT-4’s ability to generate informed consent material for genetic testing Open

Eirini Petrou, Kelly E. Ormond, Dominik Stammbach, Elliott Ash, Oliver Buchholz , et al. · 2025

The informed consent (IC) process is essential in genetic testing, yet IC materials are often difficult to read and understand, influencing patients’ decision-making. Large language models may improve the accessibility and clarity of these…

Ideas Have Consequences The Impact of Law and Economics on American Justice Open

Elliott Ash, Daniel L. Chen, Suresh Naidu · 2025

This paper empirically studies the effects of the early law-and-economics movement on the U.S. judiciary. We focus on the Manne Economics Institute for Federal Judges, an intensive economics course that trained almost half of federal judge…

Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification Open

Xiong Chen, Jingwei Ni, Yu Fan, Vilém Zouhar, Donya Rooein , et al. · 2025

We introduce Co-DETECT (Collaborative Discovery of Edge cases in TExt ClassificaTion), a novel mixed-initiative annotation framework that integrates human expertise with automatic annotation guided by large language models (LLMs). Co-DETEC…

LEXam: Benchmarking Legal Reasoning on 340 Law Exams Open

Yu Fan, Jingwei Ni, Jakob Merane, Etienne Salimbeni, Yang Tian , et al. · 2025

Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. To address this, we introduce \textsc{LEXam}, a novel benchmark derived from 340 law exams spanning 116 la…

Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning Open

Tianyi Wu, Jingwei Ni, Bryan Hooi, Jiaheng Zhang, Elliott Ash , et al. · 2025

Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to generate responses containing long-tail knowledge that was …

Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification Open

Xiong Chen, Jingwei Ni, Yu Fan, Vilém Zouhar, Donya Rooein , et al. · 2025

Can Large Language Models Capture Human Annotator Disagreements? Open

Jingwei Ni, Yu Fan, Vilém Zouhar, Donya Rooein, Alexander Hoyle , et al. · 2025

Interviews Open

Elliott Ash, Soumitra Shukla, Jason Sockin · 2025

Measuring scalar constructs in social science with LLMs Open

Hauke Licht, Rupak Sarkar, Patrick Y. Wu, Pranav Goel, Niklas Stoehr , et al. · 2025

LEXam: Benchmarking Legal Reasoning on 340 Law Exams Open

Yu Fan, Jingwei Ni, Jakob Merane, Etienne Salimbeni, Yang Tian , et al. · 2025

Interviews Open

Jason Sockin, Elliott Ash, Soumitra Shukla · 2025

The Medium Is Not the Message: Deconfounding Text Embeddings via Linear Concept Erasure Open

Yu Fan, Yang Tian, Shauli Ravfogel, Mrinmaya Sachan, Elliott Ash , et al. · 2025

DIRAS: Efficient LLM Annotation of Document Relevance for Retrieval Augmented Generation Open

Jingwei Ni, Tobias Schimanski, Meihong Lin, Mrinmaya Sachan, Elliott Ash , et al. · 2025

The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure Open

Yu Fan, Yang Tian, Shauli Ravfogel, Mrinmaya Sachan, Elliott Ash , et al. · 2025

Worker Rights in Collective Bargaining Open

Benjamin W. Arold, Elliott Ash, W. Bentley MacLeod, Suresh Naidu · 2025

The Value of Worker Rights in Collective Bargaining Open

Benjamin W. Arold, Elliott Ash, W. Bentley MacLeod, Suresh Naidu · 2025

BallotBot: Can AI Strengthen Democracy? Open

Elliott Ash, Sergio Galletta, Giacomo Opocher · 2025

A large language model-based approach to quantifying the effects of social determinants in liver transplant decisions Open

Emily Robitschek, Asal Bastani, Kathryn Horwath, Savyon Sordean, Mark J. Pletcher , et al. · 2024

Patient life circumstances, including social determinants of health (SDOH), shape both health outcomes and care access, contributing to persistent disparities across gender, race, and socioeconomic status. Liver transplantation exemplifies…

Automating <i>Abercrombie</i>: Machine‐learning trademark distinctiveness Open

Shivam Adarsh, Elliott Ash, Stefan Bechtold, Barton Beebe, Jeanne C. Fromer · 2024

Trademark law protects marks to enable firms to signal their products' qualities to consumers. To qualify for protection, a mark must be able to identify and distinguish goods. US courts typically locate a mark on a “spectrum of distinctiv…

From viewers to voters: Tracing Fox News’ impact on American democracy Open

Elliott Ash, Sergio Galletta, Matteo Pinna, Christopher Warshaw · 2024

This paper provides a comprehensive assessment of the effect of Fox News Channel (FNC) on the mass public's political preferences and voting behavior in the United States from 2000 to 2020. We show that FNC has shifted the ideology and par…

BallotBot: Can Chatbots Strengthen Direct Democracy? Open

Giacomo Opocher, Elliott Ash, Sergio Galletta · 2024

Aligning Large Language Models with Diverse Political Viewpoints Open

Dominik Stammbach, Philine Widmer, Eun‐Jung Cho, Caglar Gulcehre, Elliott Ash · 2024

Large language models such as ChatGPT exhibit striking political biases. If users query them about political information, they often take a normative stance. To overcome this, we align LLMs with diverse political viewpoints from 100,000 co…

DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation Open

Jingwei Ni, Tobias Schimanski, Meihong Lin, Mrinmaya Sachan, Elliott Ash , et al. · 2024

Retrieval Augmented Generation (RAG) is widely employed to ground responses to queries on domain-specific documents. But do RAG implementations leave out important information when answering queries that need an integrated analysis of info…

Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback Open

Emilia Agis Lerner, Florian E. Dorner, Elliott Ash, Naman Goel · 2024

There is a growing body of work on learning from human feedback to align various aspects of machine learning systems with human values and preferences. We consider the setting of fairness in content moderation, in which human feedback is u…

Gender and reactions to speeches in German parliamentary debates Open

Elliott Ash, Johann Krümmel, Jonathan Slapin · 2024

Are nonverbal reactions during parliamentary debate gendered? Do male and female members of parliament (MPs) experience applause or jeering differently? In short, yes, and the gendered nature of a speech matters. Using an original corpus o…

Translating Legalese Open

Elliott Ash, Aniket Kesari, Suresh Naidu, L. Song, Dominik Stammbach · 2024

Judicial opinions are written to be persuasive and could build public trust in court decisions, yet they can be difficult for non-experts to understand. We present a pipeline for using an AI assistant to generate simplified summaries of ju…

Scaling laws: legal and social complexity in US localities Open

Elliott Ash, Christoph Goessmann, Suresh Naidu · 2024

Law sets out the rules for society and the economy, particularly important for interactions between strangers. Legal code is a form of non-rival infrastructure, a public good important for investment and innovation. This paper investigates…

Elliott Ash YOU? Author Swipe