Across four clinical inference tasks, six LLMs answer paired knowledge probes at 92% accuracy but the main reasoning tasks at 25%, indicating a systematic knowledge-reasoning gap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference
Across four clinical inference tasks, six LLMs answer paired knowledge probes at 92% accuracy but the main reasoning tasks at 25%, indicating a systematic knowledge-reasoning gap.