# Building Human-like Communicative Intelligence: A Grounded Perspective arXiv: https://arxiv.org/abs/2201.02734 ยท HTML: https://mlsanity.com/paper/2201.02734/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Builds on 33 of its 175 references that are in the map. - First posted on arXiv 2 Jan 2022. ## Builds on (most cited first, 30 of 33) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020) - [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016) - [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019) - [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019) - [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017) - [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020) - [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020) - [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018) - [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018) - [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018) - [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017) - [Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective](https://mlsanity.com/paper/2003.00330/) (2020) - [BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance](https://mlsanity.com/paper/1911.02969/) (2019) - [Evolved Policy Gradients](https://mlsanity.com/paper/1802.04821/) (2018) - [Evolution-Guided Policy Gradient in Reinforcement Learning](https://mlsanity.com/paper/1805.07917/) (2018) - [Towards an integration of deep learning and neuroscience](https://mlsanity.com/paper/1606.03813/) (2016) - [Towards deep learning with segregated dendrites](https://mlsanity.com/paper/1610.00161/) (2016) - [Self-supervised learning through the eyes of a child](https://mlsanity.com/paper/2007.16189/) (2020) - [CEM-RL: Combining evolutionary and gradient-based methods for policy search](https://mlsanity.com/paper/1810.01222/) (2018) - [Grounded Language Learning Fast and Slow](https://mlsanity.com/paper/2009.01719/) (2020) - [Environmental drivers of systematicity and generalization in a situated agent](https://mlsanity.com/paper/1910.00571/) (2019) - [Learning Dynamic Belief Graphs to Generalize on Text-Based Games](https://mlsanity.com/paper/2002.09127/) (2020) - [Evaluating Models' Local Decision Boundaries via Contrast Sets](https://mlsanity.com/paper/2004.02709/) (2020) - [Language (Re)modelling: Towards Embodied Language Understanding](https://mlsanity.com/paper/2005.00311/) (2020) - [Knowledge is Never Enough: Towards Web Aided Deep Open World Recognition](https://mlsanity.com/paper/1906.01258/) (2019) - [Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research](https://mlsanity.com/paper/1610.07432/) (2016) - [Deep Predictive Learning in Neocortex and Pulvinar](https://mlsanity.com/paper/2006.14800/) (2020) - [A Paradigm for Situated and Goal-Driven Language Learning](https://mlsanity.com/paper/1610.03585/) (2016) ## Built on by (most cited first, 4 of 4) - [InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context](https://mlsanity.com/paper/2406.12203/) (2024) - [Artificial Intelligence for Health Message Generation: Theory, Method, and an Empirical Study Using Prompt Engineering](https://mlsanity.com/paper/2212.07507/) (2022) - [Rethinking the Evaluating Framework for Natural Language Understanding in AI Systems: Language Acquisition as a Core for Future Metrics](https://mlsanity.com/paper/2309.11981/) (2023) - [Can humans help BERT gain "confidence"?](https://mlsanity.com/paper/2309.06580/) (2023) ## Abstract (arXiv) Modern Artificial Intelligence (AI) systems excel at diverse tasks, from image classification to strategy games, even outperforming humans in many of these domains. After making astounding progress in language learning in the recent decade, AI systems, however, seem to approach the ceiling that does not reflect important aspects of human communicative capacities. Unlike human learners, communicative AI systems often fail to systematically generalize to new data, suffer from sample inefficiency, fail to capture common-sense semantic knowledge, and do not translate to real-world communicative situations. Cognitive Science offers several insights on how AI could move forward from this point. This paper aims to: (1) suggest that the dominant cognitively-inspired AI directions, based on nativist and symbolic paradigms, lack necessary substantiation and concreteness to guide progress in modern AI, and (2) articulate an alternative, "grounded", perspective on AI advancement, inspired by Embodied, Embedded, Extended, and Enactive Cognition (4E) research. I review results on 4E research lines in Cognitive Science to distinguish the main aspects of naturalistic learning conditions that play causal roles for human language development. I then use this analysis to propose a list of concrete, implementable components for building "grounded" linguistic intelligence. These components include embodying machines in a perception-action cycle, equipping agents with active exploration mechanisms so they can build their own curriculum, allowing agents to gradually develop motor abilities to promote piecemeal language development, and endowing the agents with adaptive feedback from their physical and social environment. I hope that these ideas can direct AI research towards building machines that develop human-like language abilities through their experiences with the world.