mlsanityData to 14 Oct 2026

Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems

arXiv 2109.09904 ↗First posted 21 Sep 2021cs.AIcited by 36

Not on the map. Why?

Abstract (arXiv)

Despite the surprising power of many modern AI systems that often learn their own representations, there is significant discontent about their inscrutability and the attendant problems in their ability to interact with humans. While alternatives such as neuro-symbolic approaches have been proposed, there is a lack of consensus on what they are about. There are often two independent motivations (i) symbols as a lingua franca for human-AI interaction and (ii) symbols as system-produced abstractions used by the AI system in its internal reasoning. The jury is still out on whether AI systems will need to use symbols in their internal reasoning to achieve general intelligence capabilities. Whatever the answer there is, the need for (human-understandable) symbols in human-AI interaction seems quite compelling. Symbols, like emotions, may well not be sine qua non for intelligence per se, but they will be crucial for AI systems to interact with us humans -- as we can neither turn off our emotions nor get by without our symbols. In particular, in many human-designed domains, humans would be interested in providing explicit (symbolic) knowledge and advice -- and expect machine explanations in kind. This alone requires AI systems to to maintain a symbolic interface for interaction with humans. In this blue sky paper, we argue this point of view, and discuss research directions that need to be pursued to allow for this type of human-AI interaction.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 11 of its 32 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

11 of 32 references.

References · 11

  1. 2017Deep reinforcement learning from human preferencescited by 3,912
  2. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  3. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  4. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 151
  5. 2017Visualizing and Understanding Atari Agentscited by 141
  6. 2016The Off-Switch Gamecited by 97
  7. 2018Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specificationscited by 72
  8. 2020Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentationcited by 42
  9. 2019Learning First-Order Symbolic Representations for Planning from the Structure of the State Spacecited by 38
  10. 2020Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representationscited by 32
  11. 2019Challenges of Human-Aware AI Systemscited by 13

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 8; 2023: 12; 2024: 9; 2025: 6.

36 papers.

Sort:

By area:

  1. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 207
  2. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  3. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 53
  4. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 37
  5. 2023Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsalcited by 33
  6. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  7. 2022Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversitycited by 22
  8. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  9. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  10. 2022Boosting Object Representation Learning via Motion and Object Continuitycited by 17
  11. 2024Neural Concept Bindercited by 14
  12. 2024Challenges in Human-Agent Communicationcited by 12
24 more
  1. 2024HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learningcited by 11
  2. 2022Symbol Guided Hindsight Priors for Reward Learning from Human Preferencescited by 8
  3. 2022Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferencescited by 7
  4. 2023Egocentric Planning for Scalable Embodied Task Achievementcited by 7
  5. 2024Formal Explanations for Neuro-Symbolic AIcited by 6
  6. 2021Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learningcited by 5
  7. 2023Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspectivecited by 5
  8. 2023How Faithful are Self-Explainable GNNs?cited by 5
  9. 2022Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansioncited by 4
  10. 2023Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learningcited by 4
  11. 2023PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planningcited by 4
  12. 2025Online inductive learning from answer sets for efficient reinforcement learning explorationcited by 4
  13. 2022Integrating AI Planning with Natural Language Processing: A Combination of Explicit and Tacit Knowledgecited by 3
  14. 2023Data Driven Reward Initialization for Preference based Reinforcement Learningcited by 3
  15. 2025Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networkscited by 3
  16. 2023A State Augmentation based approach to Reinforcement Learning from Human Preferencescited by 2
  17. 2023Rethinking the Evaluating Framework for Natural Language Understanding in AI Systems: Language Acquisition as a Core for Future Metricscited by 2
  18. 2023Goal Alignment: A Human-Aware Account of Value Alignment Problemcited by 1
  19. 2025On the Role of Domain Experts in Creating Effective Tutoring Systemscited by 1
  20. 2024Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshopcited by 0
  21. 2024An Epistemic Human-Aware Task Planner which Anticipates Human Beliefs and Decisionscited by 0
  22. 2025NatSGLD: A Dataset with Speech, Gesture, Logic, and Demonstration for Robot Learning in Natural Human-Robot Interactioncited by 0
  23. 2025Hybrid Learners Do Not Forget: A Brain-Inspired Neuro-Symbolic Approach to Continual Learningcited by 0
  24. 2025What Do You Mean? Exploring How Humans and AI Interact with Symbols and Meanings in Their Interactionscited by 0