Eric Horvitz

Chief Scientific Officer

Connect on LinkedIn

出版物

Eric Horvitz

出版物

Can Revealed Preferences Clarify LLM Alignment and Steering?

Performance of a large language model on the reasoning tasks of a physician

Exploring the Future of AI in Clinical Collaboration: A Study on Tumor Board Case Preparation

MEMENTO: Teaching LLMs to Manage Their Own Context

Not Another EHR: Reimagining Physician Information Needs with Generative AI Technology

Media Integrity and Authentication: Status, Directions, and Futures

New Future of Work Report 2025

The Collaboration Gap

Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets

Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning

Strengthening nucleic acid biosecurity screening against generative protein design tools

The Illusion of Readiness in Health AI

CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation

Sequential Diagnosis with Language Models

Navigating Rifts in Human-LLM Grounding: Study and Benchmark

Rapid and accurate prediction of protein homo-oligomer symmetry using Seq2Symm

Toward AI-Resilient Screening of Nucleic Acid Synthesis Orders: Process, Results, and Recommendations

Challenges in Human-Agent Communication

Food Choice Mimicry on a Large University Campus

From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond

Improving Instruction-Following in Language Models through Activation Steering

Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification

“Is This It?”: Towards Ecologically Valid Benchmarks for Situated Collaboration

Measuring and shaping the nutritional environment via food sales logs: case studies of campus-wide food choice and a call to action

MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

Will AI accelerate or delay the race to net-zero emissions?

AI-Powered Reminders for Collaborative Tasks: Experiences and Futures

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine

The Rise of the AI Co-Pilot: Lessons for Design from Aviation and Beyond

Benchmarking Spatial Relationships in Text-to-Image Generation

Sparks of Artificial General Intelligence: Early experiments with GPT-4

Capabilities of GPT-4 on Medical Challenge Problems

Disparate Impacts on Online Information Access during the COVID-19 Pandemic

Continual Learning about Objects in the Wild: An Interactive Approach

Who Goes First? Influences of Human-AI Workflow on Decision Making in Clinical Imaging

Bursting Scientific Filter Bubbles: Boosting Innovation Via Novel Author Discovery

Computational Lens on Cognition: Study of Autobiographical Versus Imagined Stories with Large-Scale Language Models

Formation of Social Ties Predicts Food Choice: A Campus-wide Longitudinal Study

Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature

AMP: Authentication of Media via Provenance

Understanding Failures of Deep Networks via Robust Feature Extraction

Exploiting structured data for learning contagious diseases under incomplete testing

Platform for Situated Intelligence

Extracting a Knowledge Base of Mechanisms from COVID-19 Papers

Population-Scale Study of Human Needs During the COVID-19 Pandemic: Analysis and Implications

Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork

Learning to Complement Humans

Multi-Stakeholder Media Provenance Management to Counter Synthetic Media Risks in News Publishing

An Empirical Analysis of Backward Compatibility in Machine Learning Systems

PACT: Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing

SQuINTing at VQA Models: Introspecting VQA Models with Sub-Questions

Configuring Audiences: A Case Study of Email Communication

PACT: Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing (TR)

Characterizing Search-Engine Traffic to Internet Research Agency Web Properties

Now, Over Here: Leveraging Extended Attentional Capabilities in Human-Robot Interaction.

Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations

Recollection versus Imagination: Exploring Human Memory and Cognition via Neural Language Models

Efficient Forward Architecture Search

Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling

Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance

Optimal Freshness Crawl Under Politeness Constraints

Situated Interaction overview

Guidelines for Human-AI Interaction

Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution

Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff

Traffic Updates: Saying a Lot While Revealing a Little

Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure

Discovering Blind Spots in Reinforcement Learning

Optimizing Interventions via Offline Policy Evaluation: Studies in Citizen Science

Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach

Wi-Fly: Widespread Opportunistic Connectivity via Commercial Air Transport

Geographic and Temporal Trends in Fake News Consumption During the 2016 US Presidential Election

A study in scene shaping: Adjusting F-formations in the wild

What Went Wrong and Why? Diagnosing Situated Interaction Failures in the Wild

Risk-Aware Planning: Methods and Case Study on Safe Driving Routes

Patient Risk Stratiï¬cation with Time-Varying Parameters: A Multitask Learning Approach