Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Emergent Communication Under Misinformation
Heeyoung Lee, Kyungwoo Song
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace random noise with a malign intermediary (misinformation) | emergent communication sender/receiver · synthetic attribute-value game, k=1..4 | TopSim | Improved |
| replace random noise with misinformation | emergent communication sender/receiver · synthetic attribute-value game, k=1..4 | generalization | Improved |
| reinitialize the intermediary at six evenly spaced intervals (new generations) (ablation) | misinformation game · synthetic attribute-value game | TopSim | Improved |
| intermediary reset (ablation) | misinformation game · synthetic attribute-value game | BosDis | No clear effect |
| add intermediary resets, in (6,7) configuration (ablation) | misinformation game · synthetic attribute-value game (N,|X|)=(6,7) | compositional generalization: 87.1 -> 96.7 | Improved |
| lower intermediary entropy coefficient (less adaptive intermediary) (ablation) | misinformation without reset · synthetic attribute-value game, k=3 | TopSim | Hurt |
| train new receivers on languages from misinformation with reset | new receiver learning · synthetic attribute-value game | learning speed | Improved |
| partial misinformation (attack subset of attributes) | misinformation game · synthetic attribute-value game, k=3 | TopSim | Improved |
| resample target attribute each step instead of prolonged exposure (ablation) | partial misinformation · synthetic attribute-value game | compositionality | Hurt |
| replace partial misinformation with positionally biased random noise (ablation) | random noise · synthetic attribute-value game, k=3 | PosDis | Hurt |
| use misinformation with reset versus random noise across message lengths 8-12 | misinformation game · synthetic attribute-value game | TopSim | Improved |
| misinformation (no reset) vs random noise in (4,18) configuration (ablation) | misinformation game · synthetic attribute-value game (N,|X|)=(4,18) | TopSim: 46.6 vs 46.6 | No clear effect |
Closest papers by meaning
- Semantics and Spatiality of Emergent Communication (NeurIPS 2024 · similarity 0.88)
- Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication (NeurIPS 2024 · similarity 0.88)
- Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments (ICLR 2024 · similarity 0.87)
- When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings (ICLR 2025 · similarity 0.87)
- Bridging semantics and pragmatics in information-theoretic emergent communication (NeurIPS 2024 · similarity 0.85)
- Unsupervised Translation of Emergent Communication (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
