Context Shapes Emergent Communication about Concepts at Different Levels of Abstraction
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
We study the communication of concepts at different levels of abstraction and in different contexts in an agent-based, interactive reference game.While playing a concept-level reference game, the neural network agents develop a communication system from scratch.We use a novel symbolic dataset that disentangles concept type (ranging from specific to generic) and context (ranging from fine to coarse) to study the influence of these factors on the emerging language.We compare two game scenarios: one in which speaker agents have access to context information (context-aware) and one in which the speaker agents do not have access to context information (context-unaware).First, we find that the agents learn higher-level concepts from the object inputs alone.Second, an analysis of the emergent communication system shows that only context-aware agents learn to communicate efficiently by adapting their messages to the context conditions and relying on context for unambiguous reference.Crucially, this behavior is not explicitly incentivized by the game, but efficient communication emerges and is driven by the availability of context alone.The emerging language we observe is reminiscent of evolutionary pressures on human languages and highlights the pivotal role of context in a communication system.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“As a difference in performance between context-unaware and context-aware conditions was not found in an earlier comparison of context-aware and context-unaware trained agents [37], this is likely due to the shared context we introduced here which seems to help the agents to come up with a mapping between messages and concepts that also generalizes very well to the test dataset.”
From The role of pragmatic mechanisms in referential communication and categorization: An emergent communication model (2026) · cites this paper as [37]
In the citing paper
“To prevent agents from communicating about lower-level features that are not relevant from a human perspective, we use a concept-level reference game for training [37,41].”
From The role of pragmatic mechanisms in referential communication and categorization: An emergent communication model (2026) · cites this paper as [37]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Kobrock, K., Ohmer, X., Bruni, E., & Gotzner, N. (2026) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1014326
“To prevent agents from communicating about lower-level features that are not relevant from a human perspective, we use a concept-level reference game for training [37,41].”
InfluentialSelf-citation
Metadata
- Authors
- Kobrock, K., Ohmer, X. I., Bruni, E., & Gotzner, N.
- Affiliations
- Osnabrück University (DE)
- Venue
- Proceedings of the Language Resources and Evaluation Conference
- Published
- 2024-05
- Pages
- 3831-3848
- ISSN
- 2522-2686
- OpenAlex
- W7131782240
- Cited by
- 0
- References
- 0
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Language Resources and Evaluation Conference (LREC) (publishedVersion)
- Funders
- Deutsche Forschungsgemeinschaft (GRK 2340, 456666331, DFG-GRK 2340)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Categorization, perception, and language
- Social Sciences › Psychology › Developmental and Educational Psychology › Child and Animal Learning Development
- Social Sciences › Arts and Humanities › Language and Linguistics › Language, Discourse, Communication Strategies
- Keywords
- emergent communication, levels of abstraction, conceptualization, context
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Context Shapes Emergent Communication about Concepts at Different Levels of Abstraction. https://app.cochat.ai/papers/10.63317/4odxjsoap6qe
- The paper
- Kobrock, K., Ohmer, X. I., Bruni, E., & Gotzner, N. (2024). Context Shapes Emergent Communication about Concepts at Different Levels of Abstraction. Proceedings of the Language Resources and Evaluation Conference. https://doi.org/10.63317/4odxjsoap6qe
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.