mlsanityData to 14 Oct 2026

Aligning Generalisation Between Humans and Machines

arXiv 2411.15626 ↗First posted 23 Nov 2024cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of AI and its participation in human-AI teams increasingly shows the need for AI alignment, that is, to make AI systems act according to our preferences. A crucial yet often overlooked aspect of these interactions is the different ways in which humans and machines generalise. In cognitive science, human generalisation commonly involves abstraction and concept learning. In contrast, AI generalisation encompasses out-of-domain generalisation in machine learning, rule-based reasoning in symbolic AI, and abstraction in neurosymbolic AI. In this perspective paper, we combine insights from AI and cognitive science to identify key commonalities and differences across three dimensions: notions of, methods for, and evaluation of generalisation. We map the different conceptualisations of generalisation in AI and cognitive science along these three dimensions and consider their role for alignment in human-AI teaming. This results in interdisciplinary challenges across AI and cognitive science that must be tackled to provide a foundation for effective and cognitively supported alignment in human-AI teaming scenarios.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 86 of its 209 references that are in the map. First posted on arXiv 23 Nov 2024.

Builds on

86 of 209 references.

References · 86

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  10. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  11. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  12. 2016Group Equivariant Convolutional Networkscited by 1,165
38 more
  1. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  2. 2018Model Cards for Model Reportingcited by 1,080
  3. 2020Object-Centric Learning with Slot Attentioncited by 876
  4. 2017A Survey on Multi-Task Learningcited by 840
  5. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  6. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  7. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  8. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  9. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  10. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  11. 2020Knowledge Graphscited by 621
  12. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  13. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
  14. 2020Learning under Concept Drift: A Reviewcited by 477
  15. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  16. 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 427
  17. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  18. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 351
  19. 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Modelscited by 336
  20. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  21. 2023AI Alignment: A Comprehensive Surveycited by 263
  22. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  23. 2022Demystifying Prompts in Language Models via Perplexity Estimationcited by 216
  24. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  25. 2020A Survey on Causal Inferencecited by 202
  26. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 196
  27. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  28. 2022Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AIcited by 171
  29. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  30. 2024Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsalcited by 118
  31. 2024When combinations of humans and AI are useful: A systematic review and meta-analysiscited by 106
  32. 2016Why does deep and cheap learning work so well?cited by 100
  33. 2023Task Contamination: Language Models May Not Be Few-Shot Anymorecited by 99
  34. 2020Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspectivecited by 95
  35. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  36. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 87
  37. 2019Measuring Compositionality in Representation Learningcited by 84
  38. 2017What Does Explainable AI Really Mean? A New Conceptualization of Perspectivescited by 72

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMscited by 3
  2. 2025Healthy Distrust in AI systemscited by 0