Ortu et al.'s main claims reproduce, but the attention-head ablation fails on underrepresented domains and varies with model, prompt, and task.
Dissecting recall of factual associations inauto-regressivelanguagemodels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Generalizability of "Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals"
Ortu et al.'s main claims reproduce, but the attention-head ablation fails on underrepresented domains and varies with model, prompt, and task.