Transformers show limited adaptive depth use on relational reasoning, with clearer evidence after finetuning on the task.
Table 1: All pretrained models used in this study, with HuggingFace identifiers, parameter counts, and number of transformer layers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
Transformers show limited adaptive depth use on relational reasoning, with clearer evidence after finetuning on the task.