# Understanding Natural Language Understanding Systems. A Critical Analysis arXiv: https://arxiv.org/abs/2303.04229 ยท HTML: https://mlsanity.com/paper/2303.04229/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Builds on 36 of its 87 references that are in the map. - First posted on arXiv 1 Mar 2023. ## Builds on (most cited first, 30 of 36) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013) - [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021) - [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022) - [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022) - [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019) - [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022) - [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022) - [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020) - [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019) - [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021) - [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019) - [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020) - [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022) - [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022) - [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022) - [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022) - [Learning and Evaluating General Linguistic Intelligence](https://mlsanity.com/paper/1901.11373/) (2019) - [Meaning without reference in large language models](https://mlsanity.com/paper/2208.02957/) (2022) - [A fine-grained comparison of pragmatic language understanding in humans and language models](https://mlsanity.com/paper/2212.06801/) (2022) - [Linguistic generalization and compositionality in modern artificial neural networks](https://mlsanity.com/paper/1904.00157/) (2019) - [Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks](https://mlsanity.com/paper/2205.05718/) (2022) - [Word meaning in minds and machines](https://mlsanity.com/paper/2008.01766/) (2020) - [Event knowledge in large language models: the gap between the impossible and the unlikely](https://mlsanity.com/paper/2212.01488/) (2022) - [Visual Commonsense in Pretrained Unimodal and Multimodal Models](https://mlsanity.com/paper/2205.01850/) (2022) ## Built on by (most cited first, 4 of 4) - [Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey](https://mlsanity.com/paper/2404.01869/) (2024) - [A theory of understanding for artificial intelligence: composability, catalysts, and learning](https://mlsanity.com/paper/2408.08463/) (2024) - [The quasi-semantic competence of LLMs: a case study on the part-whole relation](https://mlsanity.com/paper/2504.02395/) (2025) - [Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures](https://mlsanity.com/paper/2305.18915/) (2023) ## Abstract (arXiv) The development of machines that guillemotlefttalk like usguillemotright, also known as Natural Language Understanding (NLU) systems, is the Holy Grail of Artificial Intelligence (AI), since language is the quintessence of human intelligence. The brief but intense life of NLU research in AI and Natural Language Processing (NLP) is full of ups and downs, with periods of high hopes that the Grail is finally within reach, typically followed by phases of equally deep despair and disillusion. But never has the trust that we can build guillemotlefttalking machinesguillemotright been stronger than the one engendered by the last generation of NLU systems. But is it gold all that glitters in AI? do state-of-the-art systems possess something comparable to the human knowledge of language? Are we at the dawn of a new era, in which the Grail is finally closer to us? In fact, the latest achievements of AI systems have sparkled, or better renewed, an intense scientific debate on their true language understanding capabilities. Some defend the idea that, yes, we are on the right track, despite the limits that computational models still show. Others are instead radically skeptic and even dismissal: The present limits are not just contingent and temporary problems of NLU systems, but the sign of the intrinsic inadequacy of the epistemological and technological paradigm grounding them. This paper aims at contributing to such debate by carrying out a critical analysis of the linguistic abilities of the most recent NLU systems. I contend that they incorporate important aspects of the way language is learnt and processed by humans, but at the same time they lack key interpretive and inferential skills that it is unlikely they can attain unless they are integrated with structured knowledge and the ability to exploit it for language use.