# NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases

arXiv: https://arxiv.org/abs/2011.07497 · HTML: https://mlsanity.com/paper/2011.07497/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Generating Scientific Claims for Zero-Shot Scientific Fact Checking](https://mlsanity.com/paper/2203.12990/) (2022)
- [Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations](https://mlsanity.com/paper/2403.20312/) (2024)
- [Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge](https://mlsanity.com/paper/2305.05976/) (2023)
- [UnCommonSense: Informative Negative Knowledge about Everyday Concepts](https://mlsanity.com/paper/2208.09292/) (2022)
- [Completeness, Recall, and Negation in Open-World Knowledge Bases: A Survey](https://mlsanity.com/paper/2305.05403/) (2023)
- [DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data](https://mlsanity.com/paper/2505.15074/) (2025)
- [Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection](https://mlsanity.com/paper/2310.12011/) (2023)
- [Can large language models generate salient negative statements?](https://mlsanity.com/paper/2305.16755/) (2023)
- [From No to Know: Taxonomy, Challenges, and Opportunities for Negation Understanding in Multimodal Foundation Models](https://mlsanity.com/paper/2502.09645/) (2025)

## Abstract (arXiv)

Codifying commonsense knowledge in machines is a longstanding goal of artificial intelligence. Recently, much progress toward this goal has been made with automatic knowledge base (KB) construction techniques. However, such techniques focus primarily on the acquisition of positive (true) KB statements, even though negative (false) statements are often also important for discriminative reasoning over commonsense KBs. As a first step toward the latter, this paper proposes NegatER, a framework that ranks potential negatives in commonsense KBs using a contextual language model (LM). Importantly, as most KBs do not contain negatives, NegatER relies only on the positive knowledge in the LM and does not require ground-truth negative examples. Experiments demonstrate that, compared to multiple contrastive data augmentation approaches, NegatER yields negatives that are more grammatical, coherent, and informative -- leading to statistically significant accuracy improvements in a challenging KB completion task and confirming that the positive knowledge in LMs can be "re-purposed" to generate negative knowledge.