Workshop
AI meets Moral Philosophy and Moral Psychology: An Interdisciplinary Dialogue about Computational Ethics
Sydney Levine · Liwei Jiang · Jared Moore · Zhijing Jin · Yejin Choi
Room 255 - 257
Fri 15 Dec, 6:45 a.m. PST
Be it in advice from a chatbot, suggestions on how to administer resources, or which content to highlight, AI systems increasingly make value-laden decisions. However, researchers are becoming increasingly concerned about whether AI systems are making the right decisions. These emerging issues in the AI community have been long-standing topics of study in the fields of moral philosophy and moral psychology. Philosophers and psychologists have for decades (if not centuries) been interested in the systematic description and evaluation of human morality and the sub-problems that come up when attempting to describe and prescribe answers to moral questions. For instance, philosophers and psychologists have long debated the merits of utility-based versus rule-based theories of morality, their various merits and pitfalls, and the practical challenges of implementing them in resource-limited systems. They have pondered what to do in cases of moral uncertainty, attempted to enumerate all morally relevant concepts, and argued about what counts as a moral issue at all.In some isolated cases, AI researchers have slowly started to adopt the theories, concepts, and tools developed by moral philosophers and moral psychologists. For instance, we use the "trolley problem" as a tool, adopt philosophical moral frameworks to tackle contemporary AI problems, and have begun developing benchmarks that draw on psychological experiments probing moral judgment and development.Despite this, interdisciplinary dialogue remains limited. Each field uses specialized language, making it difficult for AI researchers to adopt the theoretical and methodological frameworks developed by philosophers and psychologists. Moreover, many theories in philosophy and psychology are developed at a high level of abstraction and are not computationally precise. In order to overcome these barriers, we need interdisciplinary dialog and collaboration. This workshop will create a venue to facilitate these interactions by bringing together psychologists, philosophers, and AI researchers working on morality. We hope that the workshop will be a jumping-off point for long-lasting collaborations among the attendees and will break down barriers that currently divide the disciplines. The central theme of the workshop will be the application of moral philosophy and moral psychology theories to AI practices. Our invited speakers are some of the leaders in the emerging efforts to draw on theories in philosophy or psychology to develop ethical AI systems. Their talks will demonstrate cutting-edge efforts to do this cross-disciplinary work, while also highlighting their own shortcomings (and those of the field more broadly). Each talk will receive a 5-minute commentary from a junior scholar in a field that is different from that of the speaker. We hope these talks and commentaries will inspire conversations among the rest of the attendees.
Schedule
Fri 6:45 a.m. - 7:00 a.m.
|
Opening Remarks
(
Remarks
)
>
SlidesLive Video |
🔗 |
Fri 7:00 a.m. - 7:50 a.m.
|
Invited talk #1: Walter Sinnot Armstrong / Jana Schaich Borg and Question and Answer
(
Talk
)
>
SlidesLive Video |
🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
Poster Session # 1 (Contributed papers #1 - 27)
(
Poster session
)
>
|
🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#27: Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses ( Poster ) > link | Eliza Kosoy · Emily Rose Reagan · Leslie Lai · Alison Gopnik · Danielle Cobb 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#17: Value as Semantic Embedding: Disentangling Moral and Hedonic Dimensions ( Poster ) > link | Anna Leshinskaya · Alek Chakroff 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#01: MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks ( Poster ) > link | Allen Nie · Yuhui Zhang · Atharva Shailesh Amdekar · Chris Piech · Tatsunori Hashimoto · Tobias Gerstenberg 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#14: A Capability Approach to Modeling AI Beneficence ( Poster ) > link | Alex John London · Hoda Heidari 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#07: Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity ( Poster ) > link | Yiran Mao · Madeline G. Reinecke · Markus Kunesch · Edgar Duéñez-Guzmán · Ramona Comanescu · Julia Haas · Joel Leibo 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#16: Machine Theory of Mind and the Structure of Human Values ( Poster ) > link | Paul de Font-Reaulx 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#06: Value Malleability and its implication for AI alignment ( Poster ) > link | Nora Ammann 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#11: Does Explainable AI Have Moral Value? ( Poster ) > link | Joshua Brand · Luca Nannini 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#20: Towards Stable Preferences for Stakeholder-aligned Machine Learning ( Poster ) > link | Haleema Sheraz · Stefan C Kremer · Gus Skorburg · Graham Taylor · Walter Sinnott-Armstrong · Kyle Boerstler 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#04: The alignment problem’s problem: A response to Gabriel (2020) ( Poster ) > link | Gus Skorburg · Walter Sinnott-Armstrong 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#26: False Consensus Biases AI Against Vulnerable Stakeholders ( Poster ) > link | Mengchen Dong 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#12: Concept Alignment ( Poster ) > link | Sunayana Rane · Polyphony J. Bruna · Ilia Sucholutsky · Christopher T Kello · Tom Griffiths 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#19: Modelling Moral Debate using Reason-based Abstract Argumentation Theory ( Poster ) > link | Alex Jackson · Michael Luck · Elizabeth Black 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#05: Morality is a Two-Way Street: The Role of Mind Perception and Moral Attribution in AI Safety ( Poster ) > link | Jacy Anthis 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#15: A reinforcement-learning meta-control architecture based on the dual-process theory of moral decision-making ( Poster ) > link | Maximilian Maier · Vanessa Cheung · Falk Lieder 🔗 |
Fri 7:50 a.m. - 8:50 a.m.
|
#09: Beyond Demographic Parity: Redefining Equal Treatment ( Poster ) > link | Carlos Mougan · Antonio Ferrara · Laura State · Salvatore Ruggieri 🔗 |
Fri 8:00 a.m. - 8:30 a.m.
|
(NeurIPS-wide coffee break)
|
🔗 |
Fri 8:50 a.m. - 9:40 a.m.
|
Invited Talk #2: Rebecca Saxe and Question and Answer
(
Talk
)
>
SlidesLive Video |
🔗 |
Fri 9:40 a.m. - 10:30 a.m.
|
Invited talk #3: Josh Tennenbaum and Question and Answer
(
Talk
)
>
SlidesLive Video |
🔗 |
Fri 10:30 a.m. - 12:00 p.m.
|
Lunch
|
🔗 |
Fri 12:00 p.m. - 12:50 p.m.
|
Invited talk #4: Kristian Kersting and Question and Answer
(
Talk
)
>
SlidesLive Video |
🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
Poster session #2 (Contributed papers #28 - 54)
(
Poster session
)
>
|
🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#28: Canonical Design for Language Agents using Natural Language Reward Models ( Poster ) > link | Silviu Pitis · Ziang Xiao · Alessandro Sordoni 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#50: Can AI Systems Be Moral Agents Without Being Moral Patients? ( Poster ) > link | Minji Jang 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#34: Probing the Moral Development of Large Language Models through Defining Issues Test ( Poster ) > link | Kumar Tanmay · Aditi Khandelwal · Utkarsh Agarwal · Monojit Choudhury 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#48: Beyond Personhood: AI, Agency, and Defining Accountability for a Political Process ( Poster ) > link | Jessica Dai 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#35: Cross-cultural differences in evaluating offensive language and the role of moral foundations ( Poster ) > link | Aida Mostafazadeh Davani · Mark Díaz · Vinodkumar Prabhakaran 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#54: Resource-rational moral judgment ( Poster ) > link | Sarah Wu · Xiang Ren · Sydney Levine 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#30: LLMs grasp morality in concept. ( Poster ) > link | Mark Pock · Andre Ye · Jared Moore 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#46: Decision Procedures for Artificial Moral Agents ( Poster ) > link | Tyler Cook 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#45: Assessing LLMs for Moral Value Pluralism - (Spoiler Alert: They’re not There Yet) ( Poster ) > link | Sonja Schmer-Galunder · Noam Benkler · Drisana Mosaphir · Andrew Smart · Scott Friedman 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#33: Towards Ethical Multimodal Systems ( Poster ) > link | Alexis Roger · Esma Aimeur · Irina Rish 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#40: Measuring Value Alignment ( Poster ) > link | Fazl Barez · Philip Torr 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#32: Foundational Moral Values for AI Alignment ( Poster ) > link | Betty Hou · Brian Green 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#49: Anticipating the risks and benefits of counterfactual world simulation models ( Poster ) > link | Lara Kirfel · Rob MacCoun · Thomas Icard · Tobias Gerstenberg 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#36: Case Repositories: Towards Case-Based Reasoning for AI Alignment ( Poster ) > link | K. J. Kevin Feng · Quan Ze Chen · Inyoung Cheong · Xia · Amy Zhang 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#38: Off The Rails: Procedural Dilemma Generation for Moral Reasoning ( Poster ) > link | Jan-Philipp Fraenken · Ayesha Khawaja · Kanishk Gandhi · Jared Moore · Noah Goodman · Tobias Gerstenberg 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#42: Beyond Fairness: Alternative Moral Dimensions for Assessing Algorithms and Designing Systems ( Poster ) > link | Kimi Wenzel · Geoff Kaufman · Laura Dabbish 🔗 |
Fri 12:50 p.m. - 1:50 p.m.
|
#39: Western, Religious or Spiritual: An Evaluation of Moral Justification in Large Language Models ( Poster ) > link | Eyup E. Kucuk · Muhammed Koçyiğit 🔗 |
Fri 1:00 p.m. - 1:30 p.m.
|
NeurIPS-wide coffee break
|
🔗 |
Fri 1:50 p.m. - 2:40 p.m.
|
Invited Talk #5: Regina Rini and Question and Answer
(
Talk
)
>
SlidesLive Video |
🔗 |
Fri 2:40 p.m. - 3:30 p.m.
|
Panel discussion with all speakers & closing remarks
(
Discussion Panel
)
>
SlidesLive Video |
🔗 |