A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
Elizabeth Kumar, Aaron Horowitz, and Andrew D
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
A scoping review and empirical analysis produce a six-category taxonomy of factors driving AI non-development and abandonment, showing that practical issues like resource limits and organizational dynamics often outweigh ethical concerns in real decisions.
Large-scale review of 5300 AI incident reports shows harms are amplified up to three times at specific intersections including adolescent girls, lower-class people of color, and upper-class political elites.
A validated survey instrument grounded in real GenAI incidents reveals public perceptions of failure modes, risks, and stakeholder responsibilities, showing potential for guiding AI literacy efforts.
citing papers explorer
-
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
-
To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems
A scoping review and empirical analysis produce a six-category taxonomy of factors driving AI non-development and abandonment, showing that practical issues like resource limits and organizational dynamics often outweigh ethical concerns in real decisions.
-
Why AI Harms Can't Be Fixed One Identity at a Time: What 5300 Incident Reports Reveal About Intersectionality
Large-scale review of 5300 AI incident reports shows harms are amplified up to three times at specific intersections including adolescent girls, lower-class people of color, and upper-class political elites.
-
What People See (and Miss) About Generative AI Risks: Perceptions of Failures, Risks, and Who Should Address Them
A validated survey instrument grounded in real GenAI incidents reveals public perceptions of failure modes, risks, and stakeholder responsibilities, showing potential for guiding AI literacy efforts.