# CSKG: The CommonSense Knowledge Graph

arXiv: https://arxiv.org/abs/2012.11490 · HTML: https://mlsanity.com/paper/2012.11490/

## Key facts

- Cited by 45 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 30 of 45)

- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Extracting Cultural Commonsense Knowledge at Scale](https://mlsanity.com/paper/2210.07763/) (2022)
- [Relational World Knowledge Representation in Contextual Language Models: A Review](https://mlsanity.com/paper/2104.05837/) (2021)
- [A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models](https://mlsanity.com/paper/2202.08772/) (2022)
- [Dimensions of Commonsense Knowledge](https://mlsanity.com/paper/2101.04640/) (2021)
- [GraphRAG under Fire](https://mlsanity.com/paper/2501.14050/) (2025)
- [Refined Commonsense Knowledge from Large-Scale Web Contents](https://mlsanity.com/paper/2112.04596/) (2021)
- [A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA](https://mlsanity.com/paper/2206.14989/) (2022)
- [FIRE: Food Image to REcipe generation](https://mlsanity.com/paper/2308.14391/) (2023)
- [BRAINTEASER: Lateral Thinking Puzzles for Large Language Models](https://mlsanity.com/paper/2310.05057/) (2023)
- [Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization](https://mlsanity.com/paper/2206.01532/) (2022)
- [Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset](https://mlsanity.com/paper/2109.07679/) (2021)
- [A Study of Situational Reasoning for Traffic Understanding](https://mlsanity.com/paper/2306.02520/) (2023)
- [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](https://mlsanity.com/paper/2212.07425/) (2022)
- [Knowledge-enhanced Agents for Interactive Text Games](https://mlsanity.com/paper/2305.05091/) (2023)
- [Abstractive Meeting Summarization: A Survey](https://mlsanity.com/paper/2208.04163/) (2022)
- [KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding](https://mlsanity.com/paper/2210.04105/) (2022)
- [ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains](https://mlsanity.com/paper/2410.09870/) (2024)
- [Knowledge Graphs Querying](https://mlsanity.com/paper/2305.14485/) (2023)
- [Causal Question Answering with Reinforcement Learning](https://mlsanity.com/paper/2311.02760/) (2023)
- [Natural Language Processing with Commonsense Knowledge: A Survey](https://mlsanity.com/paper/2108.04674/) (2021)
- [An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs](https://mlsanity.com/paper/2205.10661/) (2022)
- [Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks](https://mlsanity.com/paper/2409.18235/) (2024)
- [Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering](https://mlsanity.com/paper/2105.13662/) (2021)
- [Generalizable Neuro-symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/2201.06230/) (2022)
- [CoSe-Co: Text Conditioned Generative CommonSense Contextualizer](https://mlsanity.com/paper/2206.05706/) (2022)
- [GEMS: Scene Expansion using Generative Models of Graphs](https://mlsanity.com/paper/2207.03729/) (2022)
- [Commonsense Knowledge in Word Associations and ConceptNet](https://mlsanity.com/paper/2109.09309/) (2021)
- [Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods](https://mlsanity.com/paper/2201.12126/) (2022)
- [Dual Embodied-Symbolic Concept Representations for Deep Learning](https://mlsanity.com/paper/2203.00600/) (2022)

## Abstract (arXiv)

Sources of commonsense knowledge support applications in natural language understanding, computer vision, and knowledge graphs. Given their complementarity, their integration is desired. Yet, their different foci, modeling approaches, and sparse overlap make integration difficult. In this paper, we consolidate commonsense knowledge by following five principles, which we apply to combine seven key sources into a first integrated CommonSense Knowledge Graph (CSKG). We analyze CSKG and its various text and graph embeddings, showing that CSKG is well-connected and that its embeddings provide a useful entry point to the graph. We demonstrate how CSKG can provide evidence for generalizable downstream reasoning and for pre-training of language models. CSKG and all its embeddings are made publicly available to support further research on commonsense knowledge integration and reasoning.