# Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items

arXiv: https://arxiv.org/abs/1808.10627 · HTML: https://mlsanity.com/paper/1808.10627/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2018.

## Built on by (most cited first, 30 of 36)

- [Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little](https://mlsanity.com/paper/2104.06644/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Understanding by Understanding Not: Modeling Negation in Language Models](https://mlsanity.com/paper/2105.03519/) (2021)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence](https://mlsanity.com/paper/2405.15750/) (2024)
- [Benchmarks as Microscopes: A Call for Model Metrology](https://mlsanity.com/paper/2407.16711/) (2024)
- [A Targeted Assessment of Incremental Processing in Neural LanguageModels and Humans](https://mlsanity.com/paper/2106.03232/) (2021)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [Language Models Use Monotonicity to Assess NPI Licensing](https://mlsanity.com/paper/2105.13818/) (2021)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [Can Language Models Learn Typologically Implausible Languages?](https://mlsanity.com/paper/2502.12317/) (2025)
- [This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models](https://mlsanity.com/paper/2310.15941/) (2023)
- [MELA: Multilingual Evaluation of Linguistic Acceptability](https://mlsanity.com/paper/2311.09033/) (2023)
- [Can Language Models Be Tricked by Language Illusions? Easier with Syntax, Harder with Semantics](https://mlsanity.com/paper/2311.01386/) (2023)
- [Language Modelling as a Multi-Task Problem](https://mlsanity.com/paper/2101.11287/) (2021)
- [Can RNNs learn Recursive Nested Subject-Verb Agreements?](https://mlsanity.com/paper/2101.02258/) (2021)
- [TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2506.13487/) (2025)
- [Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding](https://mlsanity.com/paper/2210.14486/) (2022)
- [Schr"odinger's Tree -- On Syntax and Neural Language Models](https://mlsanity.com/paper/2110.08887/) (2021)
- [John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs](https://mlsanity.com/paper/2106.01060/) (2021)
- [Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding](https://mlsanity.com/paper/2506.14397/) (2025)
- [A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers](https://mlsanity.com/paper/2507.22337/) (2025)
- [Attention vs non-attention for a Shapley-based explanation method](https://mlsanity.com/paper/2104.12424/) (2021)
- [Making Language Models Robust Against Negation](https://mlsanity.com/paper/2502.07717/) (2025)
- [Explaining a Neural Attention Model for Aspect-Based Sentiment Classification Using Diagnostic Classification](https://mlsanity.com/paper/2103.15927/) (2021)
- [Counteracts: Testing Stereotypical Representation in Pre-trained Language Models](https://mlsanity.com/paper/2301.04347/) (2023)
- [LLMs' morphological analyses of complex FST-generated Finnish words](https://mlsanity.com/paper/2407.08269/) (2024)
- [Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs](https://mlsanity.com/paper/2101.00674/) (2021)
- [Transformers in the loop: Polarity in neural models of language](https://mlsanity.com/paper/2109.03926/) (2021)
- [Connecting degree and polarity: An artificial language learning study](https://mlsanity.com/paper/2109.06333/) (2021)

## Abstract (arXiv)

In this paper, we attempt to link the inner workings of a neural language model to linguistic theory, focusing on a complex phenomenon well discussed in formal linguis- tics: (negative) polarity items. We briefly discuss the leading hypotheses about the licensing contexts that allow negative polarity items and evaluate to what extent a neural language model has the ability to correctly process a subset of such constructions. We show that the model finds a relation between the licensing context and the negative polarity item and appears to be aware of the scope of this context, which we extract from a parse tree of the sentence. With this research, we hope to pave the way for other studies linking formal linguistics to deep learning.