Goggles is a gradient-editing module trained once per base model and frame that, when applied frozen during finetuning, causes LLMs to treat unannotated documents with a specified epistemic stance (e.g., as fiction) at 91% accuracy while preserving benchmark performance.
injustice
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An exploratory red-teaming study documents eleven cases of security, privacy, and governance failures in autonomous language-model agents with tool access and persistent memory.
citing papers explorer
-
Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing
Goggles is a gradient-editing module trained once per base model and frame that, when applied frozen during finetuning, causes LLMs to treat unannotated documents with a specified epistemic stance (e.g., as fiction) at 91% accuracy while preserving benchmark performance.
-
Agents of Chaos
An exploratory red-teaming study documents eleven cases of security, privacy, and governance failures in autonomous language-model agents with tool access and persistent memory.