Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents

• URL: http://arxiv.org/abs/2606.22207v1
• Date: Sat, 20 Jun 2026 20:08:07 GMT
• Title: Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents
• Abstract summary: This paper introduces Lexical Consensus, an experimental framework for studying grounded word learning over a structured perceptual substrate.<n>We test whether agents can acquire artificial labels for visual concepts, generalize them bidirectionally, and stabilize them across controlled settings.<n>The main result is a robust perceptual-coherence gradient: native categories are easiest to learn, coherent overextensions remain learnable, mid-range disjunctive concepts degrade, and far-disjunctive concepts approach chance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Artificial intelligence systems are commonly evaluated through task performance and behavioral imitation, but such evaluations leave open whether an artificial agent can acquire, stabilize, and use new lexical meanings from grounded experience. This paper introduces Lexical Consensus, an experimental framework for studying grounded word learning over a structured perceptual substrate. Using frozen DINOv2 visual embeddings, Carroll-style nonce words, and interpretable lexical learners plus linear baselines, we test whether agents can acquire artificial labels for visual concepts, generalize them bidirectionally, and stabilize them across controlled settings. The main result is a robust perceptual-coherence gradient: native categories are easiest to learn, coherent overextensions remain learnable, mid-range disjunctive concepts degrade, and far-disjunctive concepts approach chance. A pre-registered CIFAR-100 dissociation experiment confirms that this gradient is governed by perceptual distance rather than semantic relatedness: perceptual distance predicts acquisition accuracy (partial R^2 = 0.245, p < 1e-7), while semantic distance adds no significant explanatory power (partial R^2 = 0.002, p = 0.660). Bidirectional evaluation shows that naming and retrieval are distinct: exemplar-based mechanisms outperform centroid prototypes in label-to-image retrieval, exposing a memory-fidelity dimension separate from naming accuracy. Falsification controls, homogeneous candidate-pool evaluations, and null results on representational restructuring indicate that frozen perceptual geometry both enables lexical grounding and limits what can be acquired without representational adaptation.

Related papers

• A Dynamic-Semantics Framework for Grounding Human Referring Expressions in Visual Perceptual Data [0.0]
  We present a framework that externalizes pact state into three explicit, inspectable sets of referent-object bindings.<n>We evaluate the framework on the Stanford Repeated Reference Game corpus.
  arXiv  Detail & Related papers  (2026-08-09T12:14:10Z)
• Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors [2.27726424067057]
  Concept Activation Vectors (CAVs) represent human-interpretable concepts as directions in a model's activation space.<n>We extend CAV-based analysis to two neural speaking assessment systems: a text-based BERT grader and a speech-and-text multimodal grader based on Whisper.
  arXiv  Detail & Related papers  (2026-08-06T17:20:58Z)
• Learn to Rank: Visual Attribution by Learning Importance Ranking [58.69028273772474]
  We propose a new approach to generate visual attribution maps for computer vision models.<n>Our method produces dense, pixel-level attributions in a single forward pass with optional, few-step gradient refinement.<n>Our experiments demonstrate consistent quantitative improvements and sharper, boundary-aligned explanations.
  arXiv  Detail & Related papers  (2026-04-07T12:53:22Z)
• The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments [0.0]
  The paper argues that scientific meaning analysis motivates a distinct family of objectives - scientific usability.<n>The paper assesses static word embeddings and contextual transformer representations against these requirements.<n>As the field debates the limits of scale-first progress, measurement-ready representations offer a principled new frontier.
  arXiv  Detail & Related papers  (2026-03-10T18:08:53Z)
• Weakly-Supervised Contrastive Learning for Imprecise Class Labels [50.57424331797865]
  We introduce the concept of continuous semantic similarity'' to define positive and negative pairs.<n>We propose a graph-theoretic framework for weakly-supervised contrastive learning.<n>Our framework is highly versatile and can be applied to many weakly-supervised learning scenarios.
  arXiv  Detail & Related papers  (2025-05-28T06:50:40Z)
• Identifying and interpreting non-aligned human conceptual representations using language modeling [0.0]
  We show that congenital blindness induces conceptual reorganization in both a-modal and sensory-related verbal domains. We find that blind individuals more strongly associate social and cognitive meanings to verbs related to motion. For some verbs, representations of blind and sighted are highly similar.
  arXiv  Detail & Related papers  (2024-03-10T13:02:27Z)
• Robust Representation Learning for Unreliable Partial Label Learning [86.909511808373]
  Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth. This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels. We propose the Unreliability-Robust Representation Learning framework (URRL) that leverages unreliability-robust contrastive learning to help the model fortify against unreliable partial labels effectively.
  arXiv  Detail & Related papers  (2023-08-31T13:37:28Z)
• Semantic-aware Contrastive Learning for More Accurate Semantic Parsing [32.74456368167872]
  We propose a semantic-aware contrastive learning algorithm, which can learn to distinguish fine-grained meaning representations. Experiments on two standard datasets show that our approach achieves significant improvements over MLE baselines.
  arXiv  Detail & Related papers  (2023-01-19T07:04:32Z)
• Estimating the Uncertainty in Emotion Class Labels with Utterance-Specific Dirichlet Priors [24.365876333182207]
  We propose a novel training loss based on per-utterance Dirichlet prior distributions for verbal emotion recognition. An additional metric is used to evaluate the performance by detecting test utterances with high labelling uncertainty. Experiments with the widely used IEMOCAP dataset demonstrate that the two-branch structure achieves state-of-the-art classification results.
  arXiv  Detail & Related papers  (2022-03-08T23:30:01Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Prototypical Representation Learning for Relation Extraction [56.501332067073065]
  This paper aims to learn predictive, interpretable, and robust relation representations from distantly-labeled data. We learn prototypes for each relation from contextual information to best explore the intrinsic semantics of relations. Results on several relation learning tasks show that our model significantly outperforms the previous state-of-the-art relational models.
  arXiv  Detail & Related papers  (2021-03-22T08:11:43Z)
• Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings [67.11712279612583]
  Cycle-consistent training is widely used for learning a forward and inverse mapping between two domains of interest. We develop a conditional variational autoencoder (CVAE) approach that can be viewed as converting surjective mappings to implicit bijections. Our pipeline can capture such many-to-one mappings during cycle training while promoting graph-to-text diversity.
  arXiv  Detail & Related papers  (2020-12-14T10:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.