LMs store facts in task-specific parameter subsets, shown by inconsistent emergence across tasks during training and distinct localized parameters for the same fact.
Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DCO is an inference-time intervention that decomposes attention head outputs orthogonally to a dynamic context anchor and suppresses outlier components via Z-score to improve contextual faithfulness in Llama models.
citing papers explorer
-
LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
LMs store facts in task-specific parameter subsets, shown by inconsistent emergence across tasks during training and distinct localized parameters for the same fact.
-
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization
DCO is an inference-time intervention that decomposes attention head outputs orthogonally to a dynamic context anchor and suppresses outlier components via Z-score to improve contextual faithfulness in Llama models.