Expert-aware causal tracing localizes factual recall to specific experts in some MoE models but requires coalitions in others, using CounterFact interventions on subject embeddings.
Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models
Expert-aware causal tracing localizes factual recall to specific experts in some MoE models but requires coalitions in others, using CounterFact interventions on subject embeddings.