The Vector Grounding Problem

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Same question Not relevant

   "Understanding AI": Semantic Grounding in Large Language Models

   Holger Lyre · 2024 · Computation and Language · preprint, not peer reviewed · cited 13 times · AI summary available

   “Understanding AI” asks whether LLMs possess semantic grounding and applies theories of meaning to assess how their grounding relates to the world.

   Abstract

   Do LLMs understand the meaning of the texts they generate? Do they possess a semantic grounding? And how could we understand whether and what they understand? I start the paper with the observation that we have recently witnessed a generative turn in AI, since generative models, including LLMs, are key for self-supervised learning. To assess the question of semantic grounding, I distinguish and discuss five methodological ways. The most promising way is to apply core assumptions of theories of meaning in philosophy of mind and language to LLMs. Grounding proves to be a gradual affair with a three-dimensional distinction between functional, social and causal grounding. LLMs show basic evidenc…

2. Very close Not relevant

   The Mechanistic Emergence of Symbol Grounding in Language Models

   Shuyu Wu, Ziqiao Ma, Xiao-Xi Luo et al. · 2025 · arXiv.org · preprint, not peer reviewed · cited 6 times · Not summarized yet

   Abstract

   Symbol grounding (Harnad, 1990) describes how symbols such as words acquire their meanings by connecting to real-world sensorimotor experiences. Recent work has shown preliminary evidence that grounding may emerge in (vision-)language models trained at scale without using explicit grounding objectives. Yet, the specific loci of this emergence and the mechanisms that drive it remain largely unexplored. To address this problem, we introduce a controlled evaluation framework that systematically traces how symbol grounding arises within the internal computations through mechanistic and causal analysis. Our findings show that grounding concentrates in middle-layer computations and is implemented …

3. Very close Cites this paper Not relevant

   A Categorical Analysis of Large Language Models and Why LLMs Circumvent the Symbol Grounding Problem

   Luciano Floridi, Yi-Yang Jia, Fernando A. Tohmé · 2025 · arXiv.org · preprint, not peer reviewed · cited 5 times · Not summarized yet

   Abstract

   This paper presents a formal, categorical framework for analysing how humans and large language models (LLMs) transform content into truth-evaluated propositions about a state space of possible worlds W , in order to argue that LLMs do not solve but circumvent the symbol grounding problem.

4. Very close Cites this paper Not relevant

   Will multimodal large language models ever achieve deep understanding of the world?

   Igor Farkaš, Michal Vavrecka, S. Wermter · 2025 · Frontiers in Systems Neuroscience · cited 6 times · Not summarized yet

   Abstract

   Despite impressive performance in various tasks, large language models (LLMs) are subject to the symbol grounding problem, so from the cognitive science perspective, one can argue that they are merely statistics-driven distributional models without a deeper understanding. Modern multimodal versions of LLMs (MLLMs) are trying to avoid this problem by linking language knowledge with other modalities such as vision (Vision Language Models called VLM) or action (Vision Language Action Models called VLA) when, for instance, a robotic agent, is acting in the world. If eventually successful, MLLMs could be taken as pathway for symbol grounding. In this work, we explore the extent to which MLLMs int…

5. Very close Not relevant

   Disembodied Meaning? Generative AI and Understanding

   Jordi Vallverdú, I. Redondo · 2025 · Forum for Linguistic Studies · cited 3 times · Not summarized yet

   Abstract

   This study explores the cognitive and philosophical implications of Large Language Models (LLMs), focusing on their ability to generate meaning without embodiment. Grounded in the coherence-based semantics framework, the research challenges traditional views that emphasize the necessity of embodied cognition for meaningful language comprehension. Through a theoretical and comparative analysis, this paper examines the limitations of embodied cognition paradigms, such as the symbol grounding problem and critiques like Searle’s Chinese Room, and evaluates the practical capabilities of LLMs. The methodology integrates philosophical inquiry with empirical evidence, including case studies on LLM p…

6. Very close Not relevant

   Evaluating Large Language Models on the Frame and Symbol Grounding Problems: A Zero-shot Benchmark

   Shoko Oka · 2025 · arXiv.org · preprint, not peer reviewed · Not summarized yet

   Abstract

   Recent advancements in large language models (LLMs) have revitalized philosophical debates surrounding artificial intelligence. Two of the most fundamental challenges - namely, the Frame Problem and the Symbol Grounding Problem - have historically been viewed as unsolvable within traditional symbolic AI systems. This study investigates whether modern LLMs possess the cognitive capacities required to address these problems. To do so, I designed two benchmark tasks reflecting the philosophical core of each problem, administered them under zero-shot conditions to 13 prominent LLMs (both closed and open-source), and assessed the quality of the models' outputs across five trials each. Responses w…

7. Very close Cites this paper Uses this paper in depth Not relevant

   Are Large Language Models Intentional? The Limits of Referential Grounding

   M. García-Valdecasas · 2026 · Philosophy & Technology · cited 7 times · Not summarized yet

   Abstract

   This paper reassesses Searle’s Chinese Room argument in light of Large Language Models (LLMs). While Searle criticized computational systems for being mere “syntax manipulators,” transformer models of the kind exemplified by LLMs complicate this characterization. Earlier computational systems relied on a more rigid logical foundation, based largely on pattern recognition and mechanical substitution. By tracking patterns of use, maintaining rich contextual dependencies, and exploiting implicit regularities in large datasets, LLMs show an unprecedented capacity for semantic modelling. And yet, LLMs remain limited in several respects. For instance, even the most advanced AI model suffers from i…

8. Close Cited by this paper Not relevant

   Meaning without reference in large language models

   S. Piantadosi, F. Hill · 2022 · arXiv.org · preprint, not peer reviewed · cited 147 times · Not summarized yet

   Abstract

   The widespread success of large language models (LLMs) has been met with skepticism that they possess anything like human concepts or meanings. Contrary to claims that LLMs possess no meaning whatsoever, we argue that they likely capture important aspects of meaning, and moreover work in a way that approximates a compelling account of human cognition in which meaning arises from conceptual role. Because conceptual role is defined by the relationships between internal representational states, meaning cannot be determined from a model's architecture, training data, or objective function, but only by examination of how its internal states relate to each other. This approach may clarify why and …

Prior work it builds on

1. Close Used in depth by this paper Not relevant

   The Symbol Grounding Problem

   S. Harnad · 1990 · arXiv.org · preprint, not peer reviewed · cited 3,966 times · Not summarized yet

   Abstract

   There has been much discussion recently about the scope and limits of purely symbolic models of the mind and about the proper role of connectionism in cognitive modeling. This paper describes the "symbol grounding problem": How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their (arbitrary) shapes, be grounded in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations m…

2. Close Review Cites this paper A method it uses Not relevant

   A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates

   Raphaël Millière, Cameron Buckner · 2024 · Computation and Language · preprint, not peer reviewed · cited 62 times · AI summary available

   “A Philosophical Introduction to Language Models” surveys language models’ significance for classic debates about artificial neural networks and cognitive competence.

   Abstract

   Large language models like GPT-4 have achieved remarkable proficiency in a broad spectrum of language-based tasks, some of which are traditionally associated with hallmarks of human intelligence. This has prompted ongoing disagreements about the extent to which we can meaningfully ascribe any kind of linguistic or cognitive competence to language models. Such questions have deep philosophical roots, echoing longstanding debates about the status of artificial neural networks as cognitive models. This article -- the first part of two companion papers -- serves both as a primer on language models for philosophers, and as an opinionated survey of their significance in relation to classic debates…

3. Close Not relevant

   Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

   Brian Ichter, Anthony Brohan, Yevgen Chebotar et al. · 2022 · Conference on Robot Learning · cited 4,131 times · Not summarized yet

   Abstract

   Large language models can encode a wealth of semantic knowledge about the world. Such knowledge could be extremely useful to robots aiming to act upon high-level, temporally extended instructions expressed in natural language. However, a significant weakness of language models is that they lack real-world experience, which makes it difficult to leverage them for decision making within a given embodiment. For example, asking a language model to describe how to clean a spill might result in a reasonable narrative, but it may not be applicable to a particular agent, such as a robot, that needs to perform this task in a particular environment. We propose to provide real-world grounding by means …

4. Close Cites this paper Not relevant

   Can structural correspondences ground real world representational content in Large Language Models?

   Iwan Williams · 2025 · Mind & Language · cited 11 times · Not summarized yet

   Abstract

   Basic large language models (LLMs) have no direct contact with extra‐linguistic reality: Their inputs, outputs and training data consist solely of text. Can they represent the world beyond that text, nevertheless? This paper considers whether LLMs represent real‐world domains partly thanks to structural correspondences between their internal states and those domains. I clarify the requirements for a structural correspondence to play a genuinely content‐grounding role, and argue (i) that it is a live empirical possibility that text‐based LLMs meet those requirements with respect to real‐world contents, but (ii) that this requires carefully eliminating alternative, more deflationary, content a…

5. Close Not relevant

   Embers of autoregression show how large language models are shaped by the problem they are trained to solve

   R. Thomas McCoy, Shun-Yu Yao, Dan Friedman et al. · 2024 · Proceedings of the National Academy of Sciences of the United States of America · cited 211 times · Not summarized yet

   Abstract

   Significance ChatGPT and other large language models (LLMs) have attained unprecedented performance in AI. These systems are likely to influence a diverse range of fields, such as education, intellectual property law, and cognitive science, but they remain poorly understood. Here, we draw upon ideas in cognitive science to show that one productive way to understand these systems is by analyzing the goal that they were trained to accomplish. This perspective reveals some surprising limitations of LLMs, including difficulty on seemingly simple tasks such as counting words or reversing a list. Our empirical results have practical implications for when language models can safely be used, and the…

Papers that cite it

1. Close Not relevant

   Dissociating language and thought in large language models

   Kyle Mahowald, Anna A. Ivanova, I. Blank et al. · 2024 · Trends in Cognitive Sciences · cited 617 times · Not summarized yet

   Abstract

   Large Language Models (LLMs) have come closest among all models to date to mastering human language, yet opinions about their linguistic and cognitive capabilities remain split. Here, we evaluate LLMs using a distinction between formal linguistic competence—knowledge of linguistic rules and patterns—and functional linguistic competence—understanding and using language in the world. We ground this distinction in human neuroscience, which has shown that formal and functional competence rely on different neural mechanisms. Although LLMs are surprisingly good at formal competence, their performance on functional competence tasks remains spotty and often requires specialized fine-tuning and/or co…

2. Close Not relevant

   Does Conceptual Representation Require Embodiment? Insights From Large Language Models

   Qi-Hui Xu, Ying-Fang Peng, Minghua Wu et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 13 times · Not summarized yet

   Abstract

   To what extent can language alone give rise to complex concepts, or is embodied experience essential? Recent advancements in large language models (LLMs) offer fresh perspectives on this question. Although LLMs are trained on restricted modalities, they exhibit human-like performance in diverse psychological tasks. Our study compared representations of 4,442 lexical concepts between humans and ChatGPTs (GPT-3.5 and GPT-4) across multiple dimensions, including five key domains: emotion, salience, mental visualization, sensory, and motor experience. We identify two main findings: 1) Both models strongly align with human representations in non-sensorimotor domains but lag in sensory and motor a…

3. Close Uses this paper in depth Not relevant

   Textual Identifiability and Anchored Semantics for Evaluating World-Model Claims in Large Language Models

   Zihang Lan, Jin-Yu Yang · 2026 · IEEE Access · Not summarized yet

   Abstract

   Claims that large language models (LLMs) learn world models often conflate decodability, causal employment, and external anchoring. This Theory article separates these claims and makes their evidential requirements computable. A text-only learner is represented as a Markov kernel: equal corpus laws imply equal learned-state laws, while corpus and training-procedure discrepancies yield explicit discrimination bounds on a declared finite horizon. For internal representations, a conditional localization model identifies a target-loading subspace, and a nullspace construction determines whether a target can be changed while specified associated readouts remain invariant. Rank, stability, and int…

4. Close Not relevant

   Mechanistic indicators of understanding in large language models

   P. Beckmann, Matthieu Queloz · 2025 · Philosophical Studies · cited 14 times · Not summarized yet

   Abstract

   Large language models are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability, the emerging field probing the inner workings of LLMs, render this picture increasingly untenable—but only once those findings are integrated within a theoretical account of understanding. We propose a tiered framework for thinking about understanding in LLMs and use it to synthesize the most relevant findings to date. The framework distinguishes three hierarchical varieties of understanding, each tied to a corresponding level of computational organization: conceptual understanding emerges when a model forms “features”…

5. Close Not relevant

   Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding

   Joohwan Rhee · 2026 · arXiv.org · preprint, not peer reviewed · Not summarized yet

   Abstract

   This paper revisits the grounding problem for large language models in light of recent vector-grounding accounts. I accept the shift from classical symbol grounding to vector grounding, but argue that the current debate remains incomplete in two respects. First, reference is often treated too thinly, as if it were a fixed link between an isolated expression and an object. I argue instead that reference is profile-based, context-sensitive, discourse-level, affectively shaped, and norm-governed. Even in the human case, reference is publicly stabilized through patterns of use, correction, distinction, inference, and continuation rather than through identical private representations. Second, vec…