Even the best tested model, GPT4o-mini, falls more than 20 accuracy points short of the estimated human ceiling on a multiple-choice test and is fully correct in only about one-fourth of open-ended explanations.
"Is the Pope Catholic?" Applying Chain-of-Thought Reasoning to Understanding Conversational Implicatures
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Conversational implicatures are pragmatic inferences that require listeners to deduce the intended meaning conveyed by a speaker from their explicit utterances. Although such inferential reasoning is fundamental to human communication, recent research indicates that large language models struggle to comprehend these implicatures as effectively as the average human. This paper demonstrates that by incorporating Grice's Four Maxims into the model through chain-of-thought prompting, we can significantly enhance its performance, surpassing even the average human performance on this task.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse
Even the best tested model, GPT4o-mini, falls more than 20 accuracy points short of the estimated human ceiling on a multiple-choice test and is fully correct in only about one-fourth of open-ended explanations.