A new benchmark shows that NLI models and LLMs struggle to infer presuppositions in conditionals, and fine-tuning on other presupposition datasets does not transfer to this structure.
Presuppositions.Journal of Philosophical Logic, 2(4):447–457, 1973
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Let's CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition
A new benchmark shows that NLI models and LLMs struggle to infer presuppositions in conditionals, and fine-tuning on other presupposition datasets does not transfer to this structure.