Publications

You can also find my articles on my Google Scholar profile.

Moral Alignment for LLM Agents

Published in Proceedings of the 13th International Conference on Learning Representations (ICLR'25), 2024

We introduce the design of intrinsic reward functions for the moral alignment of LLM agents. We evaluate the robustness and generalization of the framework using Reinforcement Learning-based fine-tuning of agentic LLM systems in social dilemma environments. Thread on X

Recommended citation: Tennant, E., Hailes, S., Musolesi, M. (2025). "Moral Alignment for LLM Agents." Proceedings of the 13th International Conference on Learning Representations (ICLR'25). https://arxiv.org/abs/2410.01639

Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents

Published in Proceedings of the 7th AAAI/ACM Conference on AI, Ethics & Society (AIES'24), 2024

In this paper, we present a study of the learning dynamics of morally heterogeneous populations interacting in a social dilemma setting. We observe several types of non-trivial interactions between pro-social and anti-social agents, and find that certain classes of moral agents are able to steer selfish agents towards more cooperative behavior. Thread on X

Recommended citation: Tennant, E., Hailes, S., Musolesi, M. (2024). "Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents." Proceedings of the 7th AAAI/ACM Conference on AI, Ethics & Society (AIES'24). https://ojs.aaai.org/index.php/AIES/article/view/31736

Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto

Published in arXiv Preprint, 2023

How should we develop moral reasoning in artificial agents? Thread on X

Recommended citation: Tennant, E., Hailes, S., Musolesi, M. (2024). "Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto " arXiv 2312.01818. https://arxiv.org/abs/2312.01818 https://arxiv.org/abs/2312.01818

Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning

Published in Proceedings of the 32nd International Joint Conference On Artificial Intelligence (IJCAI'23), 2023

We define (reinforcement) learning agents based on various classic moral philosophies, and study agent behaviours and emerging outcomes in (multi-agent) social dilemma settings. Thread on X

Recommended citation: Tennant, E., Hailes, S., Musolesi, M. (2023). "Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning." Proceedings of the 32nd International Joint Conference On Artificial Intelligence (IJCAI'23) https://doi.org/10.24963/ijcai.2023/36

The Grammar of Politics, through the lens of Surveys and Web-based Social Network methods.

Published in PsyArXiv Preprint., 2021

This paper analyses language and network data from Twitter to test a hypothesis about Noun use by political Conservatives, and then compares the results against two survey studies.

Recommended citation: Karmannaya, E., & de-Wit, L. (2021, January 11). "The Grammar of Politics, through the lens of Surveys and Web-based Social Network methods." PsyArXiv . https://psyarxiv.com/v6qx5/

Monotasking or Multitasking: Designing Tasks for Crowdworkers’ Preferences.

Published in Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI’19), 2019

This paper is about the behaviours, experiences and preferences of crowdworkers, from a Human-Computer Interaction perspective.

Recommended citation: Lascău, L., Gould, S., Cox, A., Karmannaya, E., Brumby, D.. (2018). "Monotasking or Multitasking: Designing Tasks for Crowdworkers’ Preferences." CHI’19 Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. ACM, New York. https://doi.org/10.1145/3290605.3300649

Non-archival Conferences & Symposia:

Elizaveta Tennant, Stephen Hailes, Mirco Musolesi. Dynamics of Moral Behaviour in Heterogeneous Populations of Learning Agents (Extended Abstract & Poster). The 2025 Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM). Trinity College Dublin, Dublin, Ireland. June 2025.
Elizaveta Tennant, Stephen Hailes, Mirco Musolesi. Moral Alignment for AI Agents via Reinforcement Learning with Intrinsic Rewards (Poster). UK Multi-Agent Systems Symposium (UK-MAS). The Alan Turing Institute, London, UK. March 2025.

Conference Workshops:

Elizaveta Tennant, Stephen Hailes, Mirco Musolesi. Moral Intrinsic Rewards for Automated Alignment of LLM Agents (Long paper). Workshop on Scaling Self-Improving Foundation Models without Human Supervision at ICLR’2025. Singapore. April 2025.
Elizaveta Tennant, Stephen Hailes, Mirco Musolesi. A Roadmap for Human-Agent Moral Alignment: Integrating Pre-defined Intrinsic Rewards and Learned Reward Models (Short paper). Workshop on Bi-Directional Human-AI Alignment at ICLR’2025. Singapore. April 2025.
Elizaveta Tennant, Stephen Hailes, Mirco Musolesi. Moral Alignment for LLM Agents (Long paper). Workshop on Bi-Directional Human-AI Alignment at ICLR’2025. Singapore. April 2025.

Liza Tennant