Introduces the first real-world benchmark for causal relationship inference from academic texts and reports that LLMs achieve at most 0.535 F1.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can Large Language Models Infer Causal Relationships from Real-World Text?
Introduces the first real-world benchmark for causal relationship inference from academic texts and reports that LLMs achieve at most 0.535 F1.