Liza Tennant

Liza Tennant

PhD candidate in Computer Science at UCL, working on machine morality

Posts by Collection

publications

Monotasking or Multitasking: Designing Tasks for Crowdworkers’ Preferences.

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

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/

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

Published in 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.

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

Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents

Published in The Seventh 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.

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

Moral Alignment for LLM Agents

Published in arXiv Preprint., 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 LLM agents.

Recommended citation: Tennant, E., Hailes, S., Musolesi, M. (2024). "Moral Alignment for LLM Agents." arXiv 2410.01639. https://arxiv.org/abs/2410.01639 https://arxiv.org/abs/2410.01639

talks

Seminar: Social Psychology, Politics and Twitter

Published:

I gave a talk at the Darwin College Science Seminar Series, Univerity of Cambridge, about computational social science, and specifically how I conducted my research around Social / Political Psychology using language and network data from Twitter. Slides from the talk available from the OSF.

LSE Invited Talk: AI <-> Social Science (NLP, Morality and AI)

Published:

I was invited to give a long talk about the intersections of AI and Social Science to a group of students from societies at the LSE - Psychology Society, Philosophy Society, Effective Altruism Society & Google Developer Society. I talked about the methodologies behind NLP and how social scientstis can use them, and then about what social scientists can bring into AI Research in the domain of moral alignment, with specific examples from our paper ‘Modeling Moral Choies in Social Dilemmas with Multi-Agent Reinforcement Learning’.

AI Journal Club Presentation: Transformers

Published:

(Co-presented with Liam Barrett) Led a presentation and discussion about representations and processing happening in Transformer models to the AI Journal Club hosted at the UCL Department of Psychology and Language Sciences.

teaching

Guest Lecturer on NLP & Political Psychology @ UCL

Undergraduate course (1-2 lectures), UCL, Department of Psychology & Language Sciences, 2024

I was invited to teach 1-2 lectures per year, for four consecutive years (2021 - 2024), on the ‘Language and Communication’ module on the UCL BSc Psychology & Language Sciences programme. My lectures covered:

  • computaitonal analysis of language in the real world (e.g. on social media sites)
  • collecting data from social media APIs (e.g. Twitter), creating variables from this messy data, and my own research in Political Psychology and Linguistics on Twitter.
  • topics on Natural Language Processing / representation techniques
  • In 2023 I added material on more recent developments such as Neural Networks for NLP, and the techniques underlying Large Language Models such as the one used in ChatGPT.
  • Lecture Materials.
  • Extra material on NLP & LLMs.