# CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models

arXiv: https://arxiv.org/abs/2602.21978 · HTML: https://mlsanity.com/paper/2602.21978/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models](https://mlsanity.com/paper/2405.09605/) (2024)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2412.05149/) (2024)
- [The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative](https://mlsanity.com/paper/2210.13181/) (2022)
- [GPT or BERT: why not both?](https://mlsanity.com/paper/2410.24159/) (2024)
- [BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop](https://mlsanity.com/paper/2502.10645/) (2025)
- [How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments](https://mlsanity.com/paper/2408.09639/) (2024)
- [Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition](https://mlsanity.com/paper/2502.04795/) (2025)
- [Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs](https://mlsanity.com/paper/2502.13195/) (2025)
- [AntLM: Bridging Causal and Masked Language Models](https://mlsanity.com/paper/2412.03275/) (2024)
- [Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison](https://mlsanity.com/paper/2509.09009/) (2025)
- [Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions](https://mlsanity.com/paper/2501.04661/) (2025)
- [Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning](https://mlsanity.com/paper/2506.04408/) (2025)
- [Evaluating CxG Generalisation in LLMs via Construction-Based NLI Fine Tuning](https://mlsanity.com/paper/2509.16422/) (2025)

## Abstract (arXiv)

Recent work has examined language models from a linguistic perspective to better understand how they acquire language. Most existing benchmarks focus on judging grammatical acceptability, whereas the ability to interpret meanings conveyed by grammatical forms has received much less attention. We introduce the Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models (CxMP), a benchmark grounded in Construction Grammar that treats form-meaning pairings, or constructions, as fundamental linguistic units. CxMP evaluates whether models can interpret the semantic relations implied by constructions, using a controlled minimal-pair design across nine construction types, including the let-alone, caused motion, and ditransitive constructions. Our results show that while syntactic competence emerges early, constructional understanding develops more gradually and remains limited even in large language models (LLMs). CxMP thus reveals persistent gaps in how language models integrate form and meaning, providing a framework for studying constructional understanding and learning trajectories in language models.