Self-feeding language model probes mix construction-determined and model-determined signals, and a two-way variation test separates the two kinds of readings.
Lieb and Derek W
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
What Iterated Self-Feeding Probes of Language Models Measure, and a test that separates the construction from the model
Self-feeding language model probes mix construction-determined and model-determined signals, and a two-way variation test separates the two kinds of readings.