Attractor basins in transformer hidden states unify conflict and hallucination as basin competition or absence, with geometric margin outperforming entropy for detection and a scaling law governing confident hallucination rates.
Mass- editing memory in a transformer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
SCoL trains LLMs via meta-reinforcement learning to generate layer-specific update instructions that improve knowledge acquisition and retention from context streams over standard baselines.
citing papers explorer
-
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
Attractor basins in transformer hidden states unify conflict and hallucination as basin competition or absence, with geometric margin outperforming entropy for detection and a scaling law governing confident hallucination rates.
-
Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
SCoL trains LLMs via meta-reinforcement learning to generate layer-specific update instructions that improve knowledge acquisition and retention from context streams over standard baselines.