ComPaSS estimates commonsense plausibility by quantifying semantic shifts induced by augmenting sentences with related information and outperforms generative baselines on fine-grained tasks for language and vision-language models.
New Task: Question 4: <Q> Answers 4: <A> Sentences 4: Figure 5: The prompt for converting question-answer pair into sentence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Estimating Commonsense Plausibility through Semantic Shifts
ComPaSS estimates commonsense plausibility by quantifying semantic shifts induced by augmenting sentences with related information and outperforms generative baselines on fine-grained tasks for language and vision-language models.