Author name cluster

Walter Sinnott-Armstrong

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

AAAI Conference 2026 Conference Paper

Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback

Vijay Keswani
Cyrus Cousins
Breanna Nguyen
Vincent Conitzer
Hoda Heidari
Jana Schaich Borg
Walter Sinnott-Armstrong

Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of AI to dynamic human preferences should ideally account for "legitimate" changes to moral reasoning, while ignoring changes related to attention deficits, cognitive biases, or other arbitrary factors. However, common AI alignment approaches largely neglect temporal changes in preferences, posing serious challenges to proper alignment, especially in high-stakes applications of AI, e.g., in healthcare domains, where misalignment can jeopardize the trustworthiness of the system and yield serious individual and societal harms. This work investigates the extent to which people's moral preferences change over time, and the impact of such changes on AI alignment. Our study is grounded in the kidney allocation domain, where we elicit responses to pairwise comparisons of hypothetical kidney transplant patients from over 400 participants across 3-5 sessions. We find that, on average, participants change their response to the same scenario presented at different times around 6-20% of the time (exhibiting "response instability"). Additionally, we observe significant shifts in several participants' retrofitted decision-making models over time (capturing "model instability"). Predictive performance of simple AI models decreases as a function of both response and model instability. Moreover, predictive performance diminishes over time, highlighting the importance of accounting for temporal changes in preferences during training. These findings raise fundamental normative and technical challenges relevant to AI alignment, highlighting the need to better understand the object of alignment (what to align to) when user preferences change significantly over time, including the mechanisms underlying these changes.

PDF Details DOI

YNIMG Journal 2022 Journal Article

Good scientific practice in EEG and MEG research: Progress and perspectives

Guiomar Niso
Laurens R. Krol
Etienne Combrisson
A. Sophie Dubarry
Madison A. Elliott
Clément François
Yseult Héjja-Brichard
Sophie K. Herbst

Good scientific practice (GSP) refers to both explicit and implicit rules, recommendations, and guidelines that help scientists to produce work that is of the highest quality at any given time, and to efficiently share that work with the community for further scrutiny or utilization. For experimental research using magneto- and electroencephalography (MEEG), GSP includes specific standards and guidelines for technical competence, which are periodically updated and adapted to new findings. However, GSP also needs to be regularly revisited in a broader light. At the LiveMEEG 2020 conference, a reflection on GSP was fostered that included explicitly documented guidelines and technical advances, but also emphasized intangible GSP: a general awareness of personal, organizational, and societal realities and how they can influence MEEG research. This article provides an extensive report on most of the LiveMEEG contributions and new literature, with the additional aim to synthesize ongoing cultural changes in GSP. It first covers GSP with respect to cognitive biases and logical fallacies, pre-registration as a tool to avoid those and other early pitfalls, and a number of resources to enable collaborative and reproducible research as a general approach to minimize misconceptions. Second, it covers GSP with respect to data acquisition, analysis, reporting, and sharing, including new tools and frameworks to support collaborative work. Finally, GSP is considered in light of ethical implications of MEEG research and the resulting responsibility that scientists have to engage with societal challenges. Considering among other things the benefits of peer review and open access at all stages, the need to coordinate larger international projects, the complexity of MEEG subject matter, and today's prioritization of fairness, privacy, and the environment, we find that current GSP tends to favor collective and cooperative work, for both scientific and for societal reasons.

Details DOI

AAAI Conference 2021 Conference Paper

Indecision Modeling

Duncan C. McElfresh
Lok Chan
Kenzie Doyle
Walter Sinnott-Armstrong
Vincent Conitzer
Jana Schaich Borg
John P. Dickerson

AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act in ways which align with human values. Techniques for preference modeling and social choice help researchers learn and aggregate peoples’ preferences, which are used to guide AI behavior; thus, it is imperative that these learned preferences are accurate. These techniques often assume that people are willing to express strict preferences over alternatives; which is not true in practice. People are often indecisive, and especially so when their decision has moral implications. The philosophy and psychology literature shows that indecision is a measurable and nuanced behavior—and that there are several different reasons people are indecisive. This complicates the task of both learning and aggregating preferences, since most of the relevant literature makes restrictive assumptions on the meaning of indecision. We begin to close this gap by formalizing several mathematical indecision models based on theories from philosophy, psychology, and economics; these models can be used to describe (indecisive) agent decisions, both when they are allowed to express indecision and when they are not. We test these models using data collected from an online survey where participants choose how to (hypothetically) allocate organs to patients waiting for a transplant.

PDF Details

YNIMG Journal 2021 Journal Article

Some common fallacies in arguments from M/EEG data

Walter Sinnott-Armstrong
Claire Simmons

Like all humans, M/EEG researchers commit certain fallacies or mistakes in reasoning. This article surveys seven well-known but still common fallacies, including reverse inference, hasty generalization, hasty exclusion, inferring from group to individual, inferring from correlation to causation, affirming a disjunct, and false dichotomy. These fallacies are illustrated with classic EEG research by Libet and collaborators, but many researchers (not just Libet) continue to commit them in all areas of research (not just M/EEG). This article gives practical suggestions about how to spot and avoid each fallacy.

Details DOI

AIJ Journal 2020 Journal Article

Adapting a kidney exchange algorithm to align with human values

Rachel Freedman
Jana Schaich Borg
Walter Sinnott-Armstrong
John P. Dickerson
Vincent Conitzer

The efficient and fair allocation of limited resources is a classical problem in economics and computer science. In kidney exchanges, a central market maker allocates living kidney donors to patients in need of an organ. Patients and donors in kidney exchanges are prioritized using ad-hoc weights decided on by committee and then fed into an allocation algorithm that determines who gets what—and who does not. In this paper, we provide an end-to-end methodology for estimating weights of individual participant profiles in a kidney exchange. We first elicit from human subjects a list of patient attributes they consider acceptable for the purpose of prioritizing patients (e. g. , medical characteristics, lifestyle choices, and so on). Then, we ask subjects comparison queries between patient profiles and estimate weights in a principled way from their responses. We show how to use these weights in kidney exchange market clearing algorithms. We then evaluate the impact of the weights in simulations and find that the precise numerical values of the weights we computed matter little, other than the ordering of profiles that they imply. However, compared to not prioritizing patients at all, there is a significant effect, with certain classes of patients being (de)prioritized based on the human-elicited value judgments.

Details DOI

AAAI Conference 2018 Conference Paper

Adapting a Kidney Exchange Algorithm to Align With Human Values

Rachel Freedman
Jana Schaich Borg
Walter Sinnott-Armstrong
John Dickerson
Vincent Conitzer

The efﬁcient allocation of limited resources is a classical problem in economics and computer science. In kidney exchanges, a central market maker allocates living kidney donors to patients in need of an organ. Patients and donors in kidney exchanges are prioritized using ad-hoc weights decided on by committee and then fed into an allocation algorithm that determines who get what—and who does not. In this paper, we provide an end-to-end methodology for estimating weights of individual participant proﬁles in a kidney exchange. We ﬁrst elicit from human subjects a list of patient attributes they consider acceptable for the purpose of prioritizing patients (e. g. , medical characteristics, lifestyle choices, and so on). Then, we ask subjects comparison queries between patient proﬁles and estimate weights in a principled way from their responses. We show how to use these weights in kidney exchange market clearing algorithms. We then evaluate the impact of the weights in simulations and ﬁnd that the precise numerical values of the weights we computed matter little, other than the ordering of proﬁles that they imply. However, compared to not prioritizing patients at all, there is a signiﬁcant effect, with certain classes of patients being (de)prioritized based on the human-elicited value judgments.

PDF Details

AAAI Conference 2017 Conference Paper

Moral Decision Making Frameworks for Artificial Intelligence

Vincent Conitzer
Walter Sinnott-Armstrong
Jana Schaich Borg
Yuan Deng
Max Kramer

The generality of decision and game theory has enabled domain-independent progress in AI research. For example, a better algorithm for ﬁnding good policies in (PO)MDPs can be instantly used in a variety of applications. But such a general theory is lacking when it comes to moral decision making. For AI applications with a moral component, are we then forced to build systems based on many ad-hoc rules? In this paper we discuss possible ways to avoid this conclusion.

PDF Details