mlsanityData to 14 Oct 2026

"I'm Not Mad": Commonsense Implications of Negation and Contradiction

arXiv 2104.06511 ↗First posted 13 Apr 2021cs.CLcited by 26

Not on the map. Why?

Abstract (arXiv)

Natural language inference requires reasoning about contradictions, negations, and their commonsense implications. Given a simple premise (e.g., "I'm mad at you"), humans can reason about the varying shades of contradictory statements ranging from straightforward negations ("I'm not mad at you") to commonsense contradictions ("I'm happy"). Moreover, these negated or contradictory statements shift the commonsense implications of the original premise in nontrivial ways. For example, while "I'm mad" implies "I'm unhappy about something," negating the premise (i.e., "I'm not mad") does not necessarily negate the corresponding commonsense implications. In this paper, we present the first comprehensive study focusing on commonsense implications of negated statements and contradictions. We introduce ANION1, a new commonsense knowledge graph with 624K if-then rules focusing on negated and contradictory events. We then present joint generative and discriminative inference models for this new resource, providing novel empirical insights on how logical negations and commonsense contradictions reshape the commonsense implications of their original premises.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

18 of 41 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  4. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  5. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  6. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  7. 2019Abductive Commonsense Reasoningcited by 301
  8. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  9. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 243
  10. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  11. 2019WinoGrande: An Adversarial Winograd Schema Challenge at Scalecited by 204
  12. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 129
6 more
  1. 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
  2. 2019Counterfactual Story Reasoning and Generationcited by 88
  3. 2020Logic-Guided Data Augmentation and Regularization for Consistent Question Answeringcited by 78
  4. 2019Probing What Different NLP Tasks Teach Machines about Function Word Comprehensioncited by 44
  5. 2020Towards an Atlas of Cultural Commonsense for Machine Reasoningcited by 29
  6. 2020It's not a Non-Issue: Negation as a Source of Error in Machine Translationcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 11; 2023: 8; 2024: 2; 2025: 1; 2026: 2.

26 papers.

Sort:

By area:

  1. 2023ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Modelscited by 63
  2. 2022Synthetic Disinformation Attacks on Automated Fact Verification Systemscited by 44
  3. 2022CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negationcited by 39
  4. 2023PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narrativescited by 19
  5. 2023RECKONING: Reasoning through Dynamic Knowledge Encodingcited by 18
  6. 2023Discovering Knowledge-Critical Subnetworks in Pretrained Language Modelscited by 16
  7. 2022Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systemscited by 12
  8. 2023Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Modelscited by 12
  9. 2022ComFact: A Benchmark for Linking Contextual Commonsense Knowledgecited by 11
  10. 2024MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Modelscited by 9
  11. 2022UnCommonSense: Informative Negative Knowledge about Everyday Conceptscited by 8
  12. 2022Leveraging Affirmative Interpretations from Negation Improves Natural Language Understandingcited by 7
14 more
  1. 2022EvEntS ReaLM: Event Reasoning of Entity States via Language Modelscited by 7
  2. 2022A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negationscited by 5
  3. 2025Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understandingcited by 5
  4. 2022PInKS: Preconditioned Commonsense Inference with Minimal Supervisioncited by 4
  5. 2022kogito: A Commonsense Knowledge Inference Toolkitcited by 4
  6. 2021"It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systemscited by 3
  7. 2023CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Modelscited by 3
  8. 2022Some Reflections on Drawing Causal Inference using Textual Data: Parallels Between Human Subjects and Organized Textscited by 2
  9. 2024DiffuCOMET: Contextual Commonsense Knowledge Diffusioncited by 2
  10. 2021Negation-Instance Based Evaluation of End-to-End Negation Resolutioncited by 0
  11. 2023Preconditioned Visual Language Inference with Weak Supervisioncited by 0
  12. 2023Negated Complementary Commonsense using Large Language Modelscited by 0
  13. 2026MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoningcited by 0
  14. 2026Commonsense Knowledge with Negation: A Resource to Enhance Negation Understandingcited by 0