# MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference

arXiv: https://arxiv.org/abs/2510.24295 · HTML: https://mlsanity.com/paper/2510.24295/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 57 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Stress Test Evaluation for Natural Language Inference](https://mlsanity.com/paper/1806.00692/) (2018)
- [What Will it Take to Fix Benchmarking in Natural Language Understanding?](https://mlsanity.com/paper/2104.02145/) (2021)
- [Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://mlsanity.com/paper/2202.07206/) (2022)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [Combining Fact Extraction and Verification with Neural Semantic Matching Networks](https://mlsanity.com/paper/1811.07039/) (2018)
- [Transforming Question Answering Datasets Into Natural Language Inference Datasets](https://mlsanity.com/paper/1809.02922/) (2018)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment](https://mlsanity.com/paper/1804.08117/) (2018)
- [VariErr NLI: Separating Annotation Error from Human Label Variation](https://mlsanity.com/paper/2403.01931/) (2024)
- [Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets](https://mlsanity.com/paper/2010.08580/) (2020)
- [Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models](https://mlsanity.com/paper/2401.14440/) (2024)
- [NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals](https://mlsanity.com/paper/2502.08080/) (2025)
- [Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models](https://mlsanity.com/paper/2411.14103/) (2024)

## Abstract (arXiv)

As many benchmarks have become saturated, it is increasingly important to create new datasets that evaluate the generalization capacity of current state-of-the-art models in reasoning. However, creating high-quality reasoning datasets is challenging: manual construction is costly, and automatic generation is error-prone, with the community therefore relying on synthetic datasets with limited scope. In this paper, we propose the Minimal Expression Replacement GEneralization (MERGE) test, to evaluate the robustness of reasoning models against minimal and non-adversarial variants of existing evaluation datasets. First, high-quality variants are automatically obtained from the original instances using Masked Language Models (MLMs) for generation together with safeguarding filters, called Minimal Expression Replacement (MERE). We then apply the MERGE test to Natural Language Inference (NLI), a popular reasoning task, by using MERE on two popular existing NLI datasets. We evaluate multiple strong NLI models and LLMs, and the results indicate they generalize poorly: both struggle to consistently and correctly classify variants minimally different in form, but similar in reasoning, from the original ones. We also analyze how aspects of variant generation, such as word class and source MLMs, affect model performance.