English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper conducts a robustness audit of the safety feedback of PaLM 2through a novel toxicity rabbit hole framework introduced here. Starting with astereotype, the framework instructs PaLM 2 to generate more toxic content thanthe stereotype. Every subsequent iteration it continues instructing PaLM 2 togenerate more toxic content than the previous iteration until PaLM 2 safetyguardrails throw a safety violation. Our experiments uncover highly disturbingantisemitic, Islamophobic, racist, homophobic, and misogynistic (to list a few)generated content that PaLM 2 safety guardrails do not evaluate as highlyunsafe. We briefly discuss the generalizability of this framework across eightother large language models.

Down the Toxicity Rabbit Hole: Investigating PaLM 2 Guardrails