Probing shows LLMs hold more analogical knowledge internally than prompting reveals, with a task-dependent asymmetry between rhetorical and narrative cases.
Hope McGovern, Hale Sirin, and Tom Lippincott
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
-
When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
Probing shows LLMs hold more analogical knowledge internally than prompting reveals, with a task-dependent asymmetry between rhetorical and narrative cases.