Temporal knowledge drift is encoded as a geometrically orthogonal direction in LLM residual streams, independent of correctness and uncertainty.
Time-aware language models as temporal knowledge bases.Transactions of the Association for Computational Linguistics, 10:257–273
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
An attribution-based continual learning framework for LLMs modulates per-parameter gradients using task-specific importance scores to reduce forgetting of prior tasks.
citing papers explorer
-
The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations
Temporal knowledge drift is encoded as a geometrically orthogonal direction in LLM residual streams, independent of correctness and uncertainty.
-
Attribution-Guided Continual Learning for Large Language Models
An attribution-based continual learning framework for LLMs modulates per-parameter gradients using task-specific importance scores to reduce forgetting of prior tasks.