Pre-trained Language Models’ Interpretation of Evaluativity Implicature: Evidence from Gradable Adjectives Usage in Context
By saying Maria is tall, a human speaker typically implies that Maria is evaluatively tall from the speaker’s perspective. However, by using a different construction Maria is taller than Sophie, we cannot infer from Maria and Sophie’s relative heights that Maria is evaluatively tall because it is possible for Maria to be taller than Sophie in a context in which they both count as short. Can pre-trained language models (LMs) “understand” evaulativity (EVAL) inference? To what extent can they discern the EVAL salience of different constructions in a conversation? Will it help LMs’ implicitness performance if we give LMs a persona such as chill, social, and pragmatically skilled? Our study provides an approach to probing LMs’ interpretation of EVAL inference by incorporating insights from experimental pragmatics and sociolinguistics. We find that with the appropriate prompt, LMs can succeed in some pragmatic level language understanding tasks. Our study suggests that socio-pragmatics methodology can shed light on the challenging questions in NLP.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
An Account of Opinion Implicatures
While previous sentiment analysis research has concentrated on the interpretation of explicitly stated opinions and attitudes, this work initiates the computational study of a type of opinion implicature (i.e., opinion-o…
ImplicaturesSentenceSentiment AnalysisImplicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction
The rapid advancement of Large Language Models (LLMs) is positioning language at the core of human-computer interaction (HCI). We argue that advancing HCI requires attention to the linguistic foundations of interaction, …
Response GenerationDRInQ: Evaluating Conversational Implicature with Controlled Context Variation
Human conversation relies heavily on conversational implicature, in which speakers convey meanings that are suggested rather than explicitly stated. Although recent large language models exhibit strong conversational flu…
Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition
Natural language inference (NLI) is an increasingly important task for natural language understanding, which requires one to infer whether a sentence entails another. However, the ability of NLI models to make pragmatic …
DiagnosticImplicaturesNatural Language InferenceNatural Language Understanding+2