AI Paper Atlas

Research map / Large language models / AI and society

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

AAAI 2026 · Large language models › AI and society · approach: Human-centered trust and agency · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
scenarios with more feature tradeoffs (U to V/W)participant responses · Repeated kidney scenariosresponse stability: H(5)=222.23, p<0.001Hurt
higher model entropy (using more features)participant responses · Repeated kidney scenariosresponse stability: -0.117Hurt
longer reaction timeparticipant responses · Repeated kidney scenariosresponse stability: -0.081Hurt
longer time gap between sessionssession-wise logistic models · Kidney allocationmodel stability: rho = -0.12Hurt
participants being response and model unstable (C4 vs C1)BT-NN · Kidney allocation held-out choiceserror rate: +0.16Hurt
participants being response and model unstable (C4 vs C1)GPT-FT · Kidney allocation held-out choiceserror rate: +0.05Hurt
more queries since trainingBT-NN for C4 participants · Kidney allocationerror rate: significant positive slope in 3 of 4 training sessionsHurt
population-level fine-tuning (GPT-FT) instead of participant-specific modelspreference model · Kidney allocationerror rateHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy