TurnGate identifies the critical turn in multi-turn dialogues where a response would complete hidden malicious intent, outperforming baselines on the new MTID dataset while keeping over-refusal low.
Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 2representative citing papers
LLMs propagate misinformation more in lower-resource languages and lower-HDI countries, with input safety classifiers and retrieval-augmented fact-checking showing cross-lingual and regional gaps.
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.
citing papers explorer
-
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
TurnGate identifies the critical turn in multi-turn dialogues where a response would complete hidden malicious intent, outperforming baselines on the new MTID dataset while keeping over-refusal low.
-
To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs
LLMs propagate misinformation more in lower-resource languages and lower-HDI countries, with input safety classifiers and retrieval-augmented fact-checking showing cross-lingual and regional gaps.
-
Beyond Context: Large Language Models' Failure to Grasp Users' Intent
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.