# Can Peanuts Fall in Love with Distributional Semantics?

arXiv: https://arxiv.org/abs/2301.08731 · HTML: https://mlsanity.com/paper/2301.08731/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 102 references that are in the map.
- First posted on arXiv 20 Jan 2023.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [Advances in Pre-Training Distributed Word Representations](https://mlsanity.com/paper/1712.09405/) (2017)
- [BERTje: A Dutch BERT Model](https://mlsanity.com/paper/1912.09582/) (2019)
- [RobBERT: a Dutch RoBERTa-based Language Model](https://mlsanity.com/paper/2001.06286/) (2020)
- [Human Sentence Processing: Recurrence or Attention?](https://mlsanity.com/paper/2005.09471/) (2020)
- [Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming](https://mlsanity.com/paper/2010.03010/) (2020)
- [How well does surprisal explain N400 amplitude under different experimental conditions?](https://mlsanity.com/paper/2010.04844/) (2020)
- [So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements](https://mlsanity.com/paper/2109.01226/) (2021)
- [Different kinds of cognitive plausibility: why are transformers better than RNNs at predicting N400 amplitude?](https://mlsanity.com/paper/2107.09648/) (2021)
- [Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource](https://mlsanity.com/paper/1607.00225/) (2016)
- [Collateral facilitation in humans and language models](https://mlsanity.com/paper/2211.05198/) (2022)

## Built on by (most cited first, 6 of 6)

- [Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale](https://mlsanity.com/paper/2510.24963/) (2025)
- [Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language Model](https://mlsanity.com/paper/2302.08150/) (2023)
- [LLM surprisal is necessary but not sufficient to capture English garden-path effects: Evidence from joint latent modeling of reading paradigms](https://mlsanity.com/paper/2602.04489/) (2026)
- [Failures and Successes to Learn a Core Conceptual Distinction from the Statistics of Language](https://mlsanity.com/paper/2607.04523/) (2026)
- [Animate, or Inanimate, That is the Question for Large Language Models](https://mlsanity.com/paper/2408.06332/) (2024)
- [What can LLMs tell us about the mechanisms behind polarity illusions in humans? Experiments across model scales and training steps](https://mlsanity.com/paper/2603.27855/) (2026)

## Abstract (arXiv)

Context changes expectations about upcoming words - following a story involving an anthropomorphic peanut, comprehenders expect the sentence the peanut was in love more than the peanut was salted, as indexed by N400 amplitude (Nieuwland & van Berkum, 2006). This updating of expectations has been explained using Situation Models - mental representations of a described event. However, recent work showing that N400 amplitude is predictable from distributional information alone raises the question whether situation models are necessary for these contextual effects. We model the results of Nieuwland and van Berkum (2006) using six computational language models and three sets of word vectors, none of which have explicit situation models or semantic grounding. We find that a subset of these can fully model the effect found by Nieuwland and van Berkum (2006). Thus, at least some processing effects normally explained through situation models may not in fact require explicit situation models.