Linear probes recover evidence grades from LLM activations (median AUROC 71.8) across 22 models but the models' stated grades perform at chance level and the signal is largely lexical.
In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
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
-
The strength of clinical evidence is recoverable from language model representations but not from their stated grades
Linear probes recover evidence grades from LLM activations (median AUROC 71.8) across 22 models but the models' stated grades perform at chance level and the signal is largely lexical.