Best Practices for Building Agents RecapREAD HERE

Sign In Book a Demo

Research & Development

With over 50+ years of combined industry and academic experience in AI and ML operations, Arthur is proud to adopt a research-led approach to product development. Our experimental approach and expert researchers drive exclusive capabilities in LLMs, computer vision, bias mitigation, and other critical areas.

ML Research Fellows

Since Arthur’s inception, our Research Fellows program has recruited and curated relationships with top AI, ML, policy, and legal junior researchers, who spend a summer or semester with Arthur building toward a joint goal of public dissemination of a research result.

Angelina Wang

Angelina Wang

Namrata Mukhija

Namrata Mukhija

Michelle Bao

Michelle Bao

Naveen Durvasula

Naveen Durvasula

Lizzie Kumar

Lizzie Kumar

Kweku Kwegyir-Aggrey

Kweku Kwegyir-Aggrey

Sahil Verma

Sahil Verma

Publication Library

Model-Based Debiasing for Groupwise Item Fairness

Geometric Repair for Fair Classification at Any Decision Threshold

Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective

Tensions Between the Proxies of Human Values in AI

Equalizing Credit Opportunity in Algorithms: Aligning Algorithmic Fairness Research with U.S. Fair Lending Regulation

Who’s Thinking? A Push for Human-Centered Evaluation of LLMs using the XAI Playbook

Counterfactual Explanations for Machine Learning: A Review

Characterizing Anomalies with Explainable Classifiers

On the Generalizability and Predictability of Recommender Systems

Amortized Generation of Sequential Counterfactuals for Black Box Models

Robustness Disparities in Commercial Face Detection

Counterfactual Explanations for Machine Learning: Challenges Revisited

Conference Highlights & Talks

Conference highlight 1

Conference highlight 2

Conference highlight 3

Conference highlight 4