Malihe Alikhani
I am an Assistant Professor of AI and Social Justice at Northeastern University’s Khoury College of Computer Sciences. I also serve as a resident Visiting Fellow at the Brookings Institution, focusing on AI policy, the Ethics Chair of the Association for Computational Linguistics, and a member of the US Technology Policy Committee of the Association for Computing Machinery.
I develop AI systems that enhance communication, decision-making, and knowledge sharing across disciplines and populations. My work bridges academia, applied AI research, and public policy to ensure that AI serves society responsibly and effectively. I have served as a science and technology advisor in Congress and collaborated with the United Nations in Africa on initiatives using AI to support anti-violence efforts and promote equitable access to education and health.
Building on this vision, as the lead of the Contextual AI Lab, where we focus on building embodied systems that operate meaningfully within context across language, embodiment, and society to support productive interactions between humans and machines. By integrating insights from cognitive and social sciences with machine learning, our models capture the richness of human interpretation and support collaborative meaning construction.
email: m.alikhani AT northeastern.edu
Highlighted AI Policy Articles
Hype and harm:
Why we must ask harder questions about AI and its alignment with human values
Malihe Alikhani and Sabit Hassan
Published by Brookings
Recent Research Themes
AI Alignment and Human-in-the-Loop Evaluation in Collaborative Systems
Developing evaluation frameworks for AI systems embedded in interactive decision workflows. Modeling override capacity, demographic variability, distribution shift, and appropriate reliance in human–AI conversational systems.
Selected Papers:
HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations, Anthony Sicilia, Malihe Alikhani, The 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024.
Adaptive Platt Scaling with Causal Interpretations for Self-Reflective Language Model Uncertainty Estimates, Anthony Sicilia, Malihe Alikhani, Findings of the Association for Computational Linguistics: EMNLP 2025, 2025.
An Active Learning Framework for Inclusive Generation by Large Language Models, Sabit Hassan, Anthony B Sicilia, Malihe Alikhani, Proceedings of the 31st International Conference on Computational Linguistics, 2025.
Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios, Sabit Hassan, Anthony Sicilia, Malihe Alikhani, Proceedings of the 1st Workshop on Customizable NLP (CustomNLP4U), 2024. Best Paper Award
PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners, Anthony Sicilia, Katherine Atwell, Malihe Alikhani, Seong Jae Hwang, The Conference on Uncertainty in Artificial Intelligence (UAI), 2022. Best Paper Award
Uncertainty, Calibration, and Pragmatic Reasoning in Generative AI
Eliciting and modeling probabilistic beliefs in large language models operating in dialogue. Analyzing belief revision, theory of mind under uncertainty, and how calibrated uncertainty communication shapes downstream interpretation and reliance.
Selected Papers:
Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting, Anthony Sicilia and Malihe Alikhani, 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics.
Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models, Anthony Sicilia, Hyunwoo Kim, Khyathi Raghavi Chandu, Malihe Alikhani, Jack Hessel, The 62nd Annual Meeting of the Association for Computational Linguistics, 2024.
How Pragmatics Shape Articulation: A Computational Case Study in STEM ASL Discourse, Saki Imai, Lee Kezar, Laurel Aichler, Mert Inan, Erin Walker, Alicia Wooten, Lorna Quandt, Malihe Alikhani, LREC 2026.
Measuring How (Not Just Whether) VLMs Build Common Ground, Saki Imai, Mert Inan, Anthony B Sicilia, Malihe Alikhani, Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing-Natural Language Processing in the Generative AI Era, 2025.
Eliciting uncertainty in chain-of-thought to mitigate bias against forecasting harmful user behaviors, Anthony Sicilia, Malihe Alikhani, Proceedings of the Third Workshop on NLP for Positive Impact, 2024. Best Paper Award
Sycophancy, Persuasion and Behavioral Evaluation in Social Contexts
Studying and formalizing how large language models behave as decision partners in dialogue. Quantifying sycophancy as deviations from rational belief updating, measuring automation bias and persuasion effects, and analyzing how model responses alter user beliefs and decision trajectories.
Selected Papers:
Accounting for Sycophancy in Language Model Uncertainty Estimation, Anthony Sicilia, Mert Inan, Malihe Alikhani, the Association for Computational Linguistics: NAACL 2025.
BASIL: Bayesian Assessment of Sycophancy in LLMs, Katherine Atwell, Pedram Heydari, Anthony Sicilia, Malihe Alikhani, FAccT 2026.
MixDPO: Modeling Preference Strength for Pluralistic Alignment, Saki Imai, Pedram Heydari, Anthony Sicilia, Asteria Kaeberlein, Katherine Atwell, Malihe Alikhani, arXiv preprint arXiv:2601.06180, 2026.
How LLMs Influence Perceived Bias in Journalism, Asteria Kaeberlein, Malihe Alikhani, Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing, 2025.
How People Talk About Each other: Modeling Generalized Intergroup Bias and Emotion, Venkata Subrahmanyan Govindarajan, Katherine Atwell, Barea Sinno, Malihe Alikhani, David I Beaver, Junyi Jessy Li, EACL 2023.
Political Ideology and Polarization: A Multi-Dimensional Approach, Barea Sinno, Bernardo Oviedo, Katherine Atwell, Malihe Alikhani, Junyi Jessy Li, NAACL 2022.
How to Ask for Donations? Learning User-Specific Persuasive Dialogue Policies through Online Interactions, Nhat Tran, Malihe Alikhani, Diane Litman, Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization (UMAP), 2022. Best Paper Award
Studying the Effect of Moderator Biases on the Diversity of Online Discussions: A Computational Cross-Linguistic Study, Sabit Hassan, Katherine J Atwell, Malihe Alikhani, Proceedings of the Annual Meeting of the Cognitive Science Society, 2022.