Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback
Identification
- Public canonical key
- radar:r-d8fd57277adc9467f96dc77fdd9c81e5
- Authors
- Vijay Keswani · Cyrus Cousins · Breanna K. Nguyen · Vincent Conitzer · Hoda Heidari · Jana Schaich Borg · Walter P. Sinnott-Armstrong
- Reported year
- 2026
- Reported language
- en
- Source type
- conference-paper
- First detected
- 2026-11-13T12:50:28.967527+00:00
- Last metadata observation
- 2026-11-13T12:50:28.967527+00:00
- Last HTTP verification
- Not checked
Institutions reported by the source
Duke University · Carnegie Mellon University
Reported affiliation countries
US
Documentary abstract — original language
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.
Identifiers
- OPENALEX
- https://openalex.org/W7139098003
- DOI
- 10.1609/aaai.v40i44.41083
Documentary context
- Documentary family
- unknown
- Source-reported types
- conference-paper
- Publishers
- Association for the Advancement of Artificial Intelligence
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Sources
OpenAlex · Record 1
Cite this reference
Vijay Keswani; Cyrus Cousins; Breanna K. Nguyen; Vincent Conitzer; Hoda Heidari; Jana Schaich Borg; Walter P. Sinnott-Armstrong. Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback. 2026. https://doi.org/10.1609/aaai.v40i44.41083
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Vijay Keswani; Cyrus Cousins; Breanna K. Nguyen; Vincent Conitzer; Hoda Heidari; Jana Schaich Borg; Walter P. Sinnott-Armstrong. (2026). Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback. https://doi.org/10.1609/aaai.v40i44.41083
- Chicago
- Vijay Keswani; Cyrus Cousins; Breanna K. Nguyen; Vincent Conitzer; Hoda Heidari; Jana Schaich Borg; Walter P. Sinnott-Armstrong. Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback. 2026. https://doi.org/10.1609/aaai.v40i44.41083
- ISO 690
- Vijay Keswani; Cyrus Cousins; Breanna K. Nguyen; Vincent Conitzer; Hoda Heidari; Jana Schaich Borg; Walter P. Sinnott-Armstrong. Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback. 2026. https://doi.org/10.1609/aaai.v40i44.41083
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-d8fd57277adc9467f96dc77fdd9c81e5/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://doi.org/10.1609/aaai.v40i44.41083
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.