词汇共识：人工代理中的具身词汇学习与共享意义

摘要

人工智能系统通常通过任务表现和行为模仿进行评估，但这种评估方式无法确定人工代理是否能够从具身经验中获取、稳定并运用新的词汇意义。本文提出词汇共识（Lexical Consensus）这一实验框架，用于研究在结构化感知基底上的具身词汇学习。通过使用冻结的DINOv2视觉嵌入、卡罗尔式无意义词以及可解释的词汇学习器加线性基线，我们测试代理是否能够获取视觉概念的人工标签、双向泛化这些标签，并在受控环境下使其稳定。主要结果是一个稳健的感知一致性梯度：原生类别最容易学习，连贯性过度延伸仍可学习，中等范围的析取概念性能下降，而远距离析取概念则趋近随机水平。一项预先注册的CIFAR-100分离实验证实，该梯度由感知距离而非语义相关性主导：感知距离可预测习得准确率（偏R² = 0.245，p < 1e-7），而语义距离未增加显著的解释力（偏R² = 0.002，p = 0.660）。双向评估表明命名与检索存在差异：在从标签到图像的检索中，基于样例的机制优于质心原型，揭示了一个独立于命名准确性的记忆保真度维度。证伪控制、同质候选池评估以及表征重组上的零结果均表明，冻结的感知几何结构既赋能了词汇具身化，也限制了在没有表征适应的情况下能够习得的内容。

English

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.