Moral judgments become more deontological when human design of AI is visible, and designers are judged more strictly than the AI or unaided humans, creating plural and non-converging targets for value alignment.
2001.Doing Science: Design, Analysis and Communication of Scientific Research(1 ed.)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 6roles
background 3representative citing papers
PsyGAT structures conversations as dynamic temporal graphs with Psychological Expression Units and persona augmentation to reach state-of-the-art Macro F1 scores of 89.99 and 71.37 on DAIC-WoZ and E-DAIC while adding causal interpretability.
Lexical frequency is a stronger predictor of metaphor novelty than LM surprisal, with the surprisal-novelty link peaking early in training before declining as surprisal becomes more aligned with frequency.
The Wilcoxon signed-rank test routinely loses Type I error control in IR benchmarking and should be abandoned.
Origin-of-life research needs to treat the emergence of life as an evolutionary process, with LUCA already representing a complex, adapted population that implies substantial pre-LUCA history.
The work introduces a visualization framework that turns imperceptible micro-expressions into perceptible cues and outlines a planned pilot study to test effects on empathic experience.
citing papers explorer
-
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers
Moral judgments become more deontological when human design of AI is visible, and designers are judged more strictly than the AI or unaided humans, creating plural and non-converging targets for value alignment.
-
Psychologically-Grounded Graph Modeling for Interpretable Depression Detection
PsyGAT structures conversations as dynamic temporal graphs with Psychological Expression Units and persona augmentation to reach state-of-the-art Macro F1 scores of 89.99 and 71.37 on DAIC-WoZ and E-DAIC while adding causal interpretability.
-
The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
Lexical frequency is a stronger predictor of metaphor novelty than LM surprisal, with the surprisal-novelty link peaking early in training before declining as surprisal becomes more aligned with frequency.
-
Stop Using the Wilcoxon Test: Myth, Misconception and Misuse in IR Research
The Wilcoxon signed-rank test routinely loses Type I error control in IR benchmarking and should be abandoned.
-
The Origin of Life in the Light of Evolution
Origin-of-life research needs to treat the emergence of life as an evolutionary process, with LUCA already representing a complex, adapted population that implies substantial pre-LUCA history.
-
Making the Invisible Visible: Toward Micro-Expression Visualization for Empathy in Social Interaction
The work introduces a visualization framework that turns imperceptible micro-expressions into perceptible cues and outlines a planned pilot study to test effects on empathic experience.