Direction-flipped influence audits show contextual cues shift LLM moral choices by 12-18 points on average across multiple benchmarks, revealing asymmetries, backfires, and inconsistencies in 40% of conditions.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A marginalized transition model with Markov dependence and category-specific changepoint specification is developed for detecting shifts in serially correlated categorical time series, demonstrated on Canadian cloud cover observations.
citing papers explorer
-
Direction-Flipped Influence Audits Reveal Hidden Structure in Moral Choices of LLMs
Direction-flipped influence audits show contextual cues shift LLM moral choices by 12-18 points on average across multiple benchmarks, revealing asymmetries, backfires, and inconsistencies in 40% of conditions.
-
Changepoint Detection in Categorical Time Series with Application to Daily Total Cloud Cover in Canada
A marginalized transition model with Markov dependence and category-specific changepoint specification is developed for detecting shifts in serially correlated categorical time series, demonstrated on Canadian cloud cover observations.