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

arXiv: https://arxiv.org/abs/2606.22207 · HTML: https://mlsanity.com/paper/2606.22207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 20 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018)
- [Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog](https://mlsanity.com/paper/1706.08502/) (2017)
- [How agents see things: On visual representations in an emergent language game](https://mlsanity.com/paper/1808.10696/) (2018)
- [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)

## Abstract (arXiv)

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.