# Pragmatic inference of scalar implicature by LLMs

arXiv: https://arxiv.org/abs/2408.06673 · HTML: https://mlsanity.com/paper/2408.06673/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 42 references that are in the map.
- First posted on arXiv 13 Aug 2024.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition](https://mlsanity.com/paper/2004.03066/) (2020)
- [Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words](https://mlsanity.com/paper/2205.05092/) (2022)
- [Harnessing the linguistic signal to predict scalar inferences](https://mlsanity.com/paper/1910.14254/) (2019)
- [Expectations over Unspoken Alternatives Predict Pragmatic Inferences](https://mlsanity.com/paper/2304.04758/) (2023)

## Built on by (most cited first, 5 of 5)

- [Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models](https://mlsanity.com/paper/2510.04764/) (2025)
- [Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues](https://mlsanity.com/paper/2502.09120/) (2025)
- [Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction](https://mlsanity.com/paper/2510.25426/) (2025)
- [Continuous Interpretive Steering for Scalar Diversity](https://mlsanity.com/paper/2604.07006/) (2026)
- [Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation](https://mlsanity.com/paper/2607.25094/) (2026)

## Abstract (arXiv)

This study investigates how Large Language Models (LLMs), particularly BERT (Devlin et al., 2019) and GPT-2 (Radford et al., 2019), engage in pragmatic inference of scalar implicature, such as some. Two sets of experiments were conducted using cosine similarity and next sentence/token prediction as experimental methods. The results in experiment 1 showed that, both models interpret some as pragmatic implicature not all in the absence of context, aligning with human language processing. In experiment 2, in which Question Under Discussion (QUD) was presented as a contextual cue, BERT showed consistent performance regardless of types of QUDs, while GPT-2 encountered processing difficulties since a certain type of QUD required pragmatic inference for implicature. The findings revealed that, in terms of theoretical approaches, BERT inherently incorporates pragmatic implicature not all within the term some, adhering to Default model (Levinson, 2000). In contrast, GPT-2 seems to encounter processing difficulties in inferring pragmatic implicature within context, consistent with Context-driven model (Sperber and Wilson, 2002).