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.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
Annotators' competence in recognizing social influence techniques increases during the annotation process, more pronounced in experts, visibly affecting LLM performance on the resulting data.
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.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
How Annotation Trains Annotators: Competence Development in Social Influence Recognition
Annotators' competence in recognizing social influence techniques increases during the annotation process, more pronounced in experts, visibly affecting LLM performance on the resulting data.