Maarten Sap Twitter Profile Google Scholar Profile Semantic Scholar Profile

Maarten Sap

I am an assistant professor at CMU's LTI department with a courtesy appointment in HCII, and a part-time research scientist and AI safety lead at the Allen Institute for AI (AI2). My research focuses on (1) measuring and improving AI systems' social and interactional intelligence, (2) assessing and combatting social inequality, safety risks, and socio-cultural biases in human- or AI-generated language, and (3) building narrative language technologies for prosocial outcomes. I was named a 2025 Packard Fellow and a recipient of the 2025 Okawa Research Award.

I received my PhD from the University of Washington where I was advised by Noah Smith and Yejin Choi.
[bio for talks]

Recent updates:

December 2025 🏅📃: Very excited to have our paper Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond) selected for a Best Paper Award at NeurIPS 2025 (Datasets and Benchmarks Track)!! Huge congrats to the first author Liwei Jiang!!!

November 2025 💎🚀: Honored to be a Spring 2025 recipient of the Amazon Research Award for our project on measuring AI agentic safety!

October 2025 🏅⭐: I’m super excited and grateful to announce that I'm part of the 2025 class of Packard Fellows. The Packard Foundation and this fellowship will allow me to explore exciting research directions towards culturally responsible and safe AI 🌍🌈

October 2025 🔍🧑‍🎓: Due to my lab being quite full already, I'm not taking looking for any new students in this upcoming PhD application cycle 😟.

October 2025 🇨🇦🎉: Excited to be attending COLM 2025 in Montreal this October! I'll be giving a talk at the Social Sim Workshop on Unlocking Social Intelligence in AI agents. I'm also thrilled that five papers I co-authored will be presented by my amazing collaborators at COLM: HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions (led by Xuhui Zhou et al.), ALFA: Aligning LLMs to Ask Good Questions: A Case Study in Clinical Reasoning (co-led by Jimin Mun et al.), PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages, Fluid Language Model Benchmarking, and The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains.

August 2025 🌟: Incredibly honored to be one of 7 US recipients of the 2025 Okawa Research Grant from the Okawa Foundation!

August 2025 🧑‍🎓: Welcoming my first postdoc, Vasudha Varadarajan, to the lab!

[older news]

My research group:

Dan Chechelnitsky

CMU Portugal LTI PhD student
co-advised with Chrysoula Zerva

Joel Mire

LTI PhD student

Karina Halevy

LTI PhD student
co-advised with Mona Diab

Malia Morgan

Pre-doctoral Young Investigator at Ai2

Jimin Mun

LTI PhD student

Jocelyn Shen

MIT PhD student
co-advised with Cynthia Breazeal

Kynnedy Smith

HCII PhD student
co-advised with Motahhare Eslami

Vasudha Varadarajan

LTI Postdoc

Akhila Yerukola

LTI PhD student

Mingqian Zheng

LTI PhD student
co-advised with Carolyn Rosé

Xuhui Zhou

LTI PhD student

Overarching Research Themes

Themes extracted and images generated with the OpenAI API; there may be inconsistencies.

Ethics and Human-Centered AI

My research group explores the critical intersection of AI ethics and human perspectives in technology. One significant paper, [Position: AI Welfare Is Bullshit](https://philarchive.org/archive/XIAAWI), questions the assumptions about welfare considerations in AI, urging a rethink on prioritizing human impact rather than abstract welfare metrics. Additionally, the paper [Examining the Effect of Explanations of AI Privacy Redaction in AI-mediated Interactions](https://arxiv.org/abs/2603.24735) delves into how privacy concerns are addressed in AI systems and the consequences of these explanations on user interactions. Furthermore, our work on [Translating With Feeling: Centering Translator Perspectives within Translation Technologies](https://arxiv.org/abs/2604.00758) highlights the importance of including diverse voices and perspectives in AI translation technologies to foster inclusive practices.

Narrative Analysis and Empathy

My research group explores how narratives shape perceptions and empathy across various contexts. An important study, [Social Story Frames: Contextual Reasoning about Narrative Intent and Reception](https://arxiv.org/abs/2512.15925), presents a framework to analyze how narratives are interpreted and their intended impacts. Additionally, we investigate violent communication through [Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication](https://arxiv.org/abs/2505.21451), which emphasizes the complexity of narrative backstories in shaping aggressive interactions. Our efforts to enhance empathy in storytelling are expressed in [HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs](https://arxiv.org/abs/2405.17633), where we analyze how narrative styles can evoke emotional responses from readers.

AI Agents and Cooperative Interaction

My research group explores the dynamics of interaction between AI agents and human users, focusing on collaboration and cooperation. The paper [Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies](http://arxiv.org/abs/2604.15607) reveals how differences in attributes influence the effectiveness of human-agent collaboration scenarios. We also address safety evaluations in AI systems with [OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety](https://arxiv.org/abs/2507.06134), providing a guideline for assessing the safety and reliability of AI agents in practice. Additionally, our work on [Mind the Sim2Real Gap in User Simulation for Agentic Tasks](https://arxiv.org/abs/2603.11245) emphasizes the challenges of translating simulated interactions into real-world applications, highlighting the need for robust agent behaviors.

Social Intelligence in Language Models

My research group explores the underlying social intelligence that language models exhibit in the context of interaction. The work [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://arxiv.org/abs/2305.14763) investigates whether these models can genuinely understand social contexts or merely mimic responses based on patterns. Another important study, [SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions](https://arxiv.org/abs/2506.23046), extends this analysis by examining how different perspectives in social scenarios impact interactions with AI. We also introduce [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://arxiv.org/abs/2310.11667), which aims to provide metrics for assessing the social reasoning capabilities of language-based AI agents.

More about me