# Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding

arXiv: https://arxiv.org/abs/2609.13685 · HTML: https://mlsanity.com/paper/2609.13685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [Inverse scaling can become U-shaped](https://mlsanity.com/paper/2211.02011/) (2022)
- [Understanding by Understanding Not: Modeling Negation in Language Models](https://mlsanity.com/paper/2105.03519/) (2021)
- [CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation](https://mlsanity.com/paper/2211.00295/) (2022)
- [NevIR: Negation in Neural Information Retrieval](https://mlsanity.com/paper/2305.07614/) (2023)
- [Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation](https://mlsanity.com/paper/2210.03256/) (2022)
- [It's not a Non-Issue: Negation as a Source of Error in Machine Translation](https://mlsanity.com/paper/2010.05432/) (2020)
- [ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning](https://mlsanity.com/paper/2305.19426/) (2023)
- [Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation](https://mlsanity.com/paper/2406.05494/) (2024)
- [Improving negation detection with negation-focused pre-training](https://mlsanity.com/paper/2205.04012/) (2022)
- [Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models](https://mlsanity.com/paper/2305.17311/) (2023)
- [Paraphrasing in Affirmative Terms Improves Negation Understanding](https://mlsanity.com/paper/2406.07492/) (2024)
- [Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding](https://mlsanity.com/paper/2210.14486/) (2022)
- [Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism](https://mlsanity.com/paper/2310.14868/) (2023)
- [Making Language Models Robust Against Negation](https://mlsanity.com/paper/2502.07717/) (2025)
- [Revisiting subword tokenization: A case study on affixal negation in large language models](https://mlsanity.com/paper/2404.02421/) (2024)

## Abstract (arXiv)

Negation remains a longstanding challenge for both language models (LMs) and large language models (LLMs). Prior work mainly focuses on a small set of high-frequency single-word negation cues, such as not and never, with limited exploration of broader negation types and modern LLMs. To address this gap, we construct NegCue, a large-scale dataset containing over 1.8M samples spanning single-word, multi-word, and affixal negation with more than 200 unique cues. We further pre-train both encoder-only LMs and LLMs on NegCue to investigate how different negation types affect negation understanding. Experiments on five downstream benchmarks show that negation types contribute unevenly to performance gains under the same training scale. In particular, affixal negation yields the largest improvements, while the gains from the commonly studied single-word negation remain modest. Moreover, our results demonstrate that further pre-training improves negation understanding for both LMs and LLMs.