Trojan Horse Prompting injects malicious instructions into a fabricated assistant message in the API chat history, aiming to bypass Gemini's safety filters, but no quantitative evidence is provided.
Consideration Set Sampling to Analyze Undecided Respondents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Researchers in psychology characterize decision-making as a process of eliminating options. While statistical modelling typically focuses on the eventual choice, we analyze consideration sets describing, for each survey participant, all options between which the respondent is pondering. Using a German pre-election poll as a prototypical example, we give a proof of concept that consideration set sampling is easy to implement and provides the basis for an insightful structural analysis of the respondents' positions. The set-valued observations forming the consideration sets are naturally modelled as random sets, allowing to transfer regression modelling as
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message
Trojan Horse Prompting injects malicious instructions into a fabricated assistant message in the API chat history, aiming to bypass Gemini's safety filters, but no quantitative evidence is provided.