mlsanityData to 14 Oct 2026

Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge

arXiv 2209.13710 ↗First posted 27 Sep 2022cs.AIcited by 6

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Concept induction, which is based on formal logical reasoning over description logics, has been used in ontology engineering in order to create ontology (TBox) axioms from the base data (ABox) graph. In this paper, we show that it can also be used to explain data differentials, for example in the context of Explainable AI (XAI), and we show that it can in fact be done in a way that is meaningful to a human observer. Our approach utilizes a large class hierarchy, curated from the Wikipedia category hierarchy, as background knowledge.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 21 of its 58 references that are in the map. First posted on arXiv 27 Sep 2022.

Builds on

21 of 58 references.

References · 21

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  4. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  5. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  6. 2018Sanity Checks for Saliency Mapscited by 1,156
  7. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  8. 2017Interpretation of Neural Networks is Fragilecited by 444
  9. 2017The (Un)reliability of saliency methodscited by 333
  10. 2018On the Robustness of Interpretability Methodscited by 314
  11. 2019Counterfactual Visual Explanationscited by 313
  12. 2019Interpretable machine learning: definitions, methods, and applicationscited by 305
9 more
  1. 2018Metrics for Explainable AI: Challenges and Prospectscited by 260
  2. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  3. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  4. 2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
  5. 2018How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanationcited by 72
  6. 2019Understanding Neural Networks via Feature Visualization: A surveycited by 65
  7. 2018Efficient Concept Induction for Description Logicscited by 17
  8. 2017Explaining Trained Neural Networks with Semantic Web Technologies: First Stepscited by 13
  9. 2019Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract]cited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3.

6 papers.

  1. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 61
  2. 2024On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysiscited by 6
  3. 2023Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoningcited by 2
  4. 2024Aligning Generalisation Between Humans and Machinescited by 2
  5. 2024Beyond Attribution: Unified Concept-Level Explanationscited by 1
  6. 2023What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Combining Machine Learning and Ontology: A Systematic Literature Review
  2. 2026Explainable AI: Learning from the Learners
  3. 2023Dual Box Embeddings for the Description Logic EL++
  4. 2026Ontology-Grounded, Reasoner-Verified Benchmarks for Evaluating LLM Reasoning in Scientific AI
  5. 2026GrOIL: Graph-Grounded Domain Ontology Induction with Constrained LLM Mediation ↗
  6. 2023Neuro-Symbolic RDF and Description Logic Reasoners: The State-Of-The-Art and Challenges
  7. 2026Challenges in Evaluating Explanation Methods for Static and Evolving Data
  8. 2026X-SYS: A Reference Architecture for Interactive Explanation Systems