# Expectations over Unspoken Alternatives Predict Pragmatic Inferences

arXiv: https://arxiv.org/abs/2304.04758 · HTML: https://mlsanity.com/paper/2304.04758/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 71 references that are in the map.
- First posted on arXiv 7 Apr 2023.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behavior](https://mlsanity.com/paper/2006.01912/) (2020)
- [Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition](https://mlsanity.com/paper/2004.03066/) (2020)
- [Stop Measuring Calibration When Humans Disagree](https://mlsanity.com/paper/2210.16133/) (2022)
- [Human Sentence Processing: Recurrence or Attention?](https://mlsanity.com/paper/2005.09471/) (2020)
- [Investigating Reasons for Disagreement in Natural Language Inference](https://mlsanity.com/paper/2209.03392/) (2022)
- [Harnessing the linguistic signal to predict scalar inferences](https://mlsanity.com/paper/1910.14254/) (2019)
- [BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations](https://mlsanity.com/paper/2010.02686/) (2020)
- [Are Language Models Worse than Humans at Following Prompts? It's Complicated](https://mlsanity.com/paper/2301.07085/) (2023)
- [Scalar Adjective Identification and Multilingual Ranking](https://mlsanity.com/paper/2105.01180/) (2021)
- [Detecting and ordering adjectival scalemates](https://mlsanity.com/paper/1504.08102/) (2015)

## Built on by (most cited first, 9 of 9)

- [Information Value: Measuring Utterance Predictability as Distance from Plausible Alternatives](https://mlsanity.com/paper/2310.13676/) (2023)
- [SEA-HELM: Southeast Asian Holistic Evaluation of Language Models](https://mlsanity.com/paper/2502.14301/) (2025)
- [BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2309.06085/) (2023)
- [Evaluating statistical language models as pragmatic reasoners](https://mlsanity.com/paper/2305.01020/) (2023)
- [Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom](https://mlsanity.com/paper/2404.19509/) (2024)
- [Pragmatic inference of scalar implicature by LLMs](https://mlsanity.com/paper/2408.06673/) (2024)
- [Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue](https://mlsanity.com/paper/2605.00506/) (2026)
- [Towards an Analysis of Discourse and Interactional Pragmatic Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2408.03074/) (2024)
- [Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues](https://mlsanity.com/paper/2502.09120/) (2025)

## Abstract (arXiv)

Scalar inferences (SI) are a signature example of how humans interpret language based on unspoken alternatives. While empirical studies have demonstrated that human SI rates are highly variable -- both within instances of a single scale, and across different scales -- there have been few proposals that quantitatively explain both cross- and within-scale variation. Furthermore, while it is generally assumed that SIs arise through reasoning about unspoken alternatives, it remains debated whether humans reason about alternatives as linguistic forms, or at the level of concepts. Here, we test a shared mechanism explaining SI rates within and across scales: context-driven expectations about the unspoken alternatives. Using neural language models to approximate human predictive distributions, we find that SI rates are captured by the expectedness of the strong scalemate as an alternative. Crucially, however, expectedness robustly predicts cross-scale variation only under a meaning-based view of alternatives. Our results suggest that pragmatic inferences arise from context-driven expectations over alternatives, and these expectations operate at the level of concepts.