Research map / Large language models / Language, safety and interpretability
Linking Emergent and Natural Languages via Corpus Transfer
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use hard rather than soft Gumbel-softmax (ablation) | emergent communication pre-training · downstream tasks | downstream performance | No clear effect |
| pre-train on an emergent communication corpus | image captioning · MS-COCO, fast adaptation | CIDEr | Helped |
| increase MS-COCO fine-tuning data from 5,000 samples to more than 50,000 samples | image captioning with EC or natural-language pre-training · MS-COCO | CIDEr across fine-tuning epochs | Mixed |
Closest papers by meaning
- Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments (ICLR 2024 · similarity 0.89)
- Understanding Emergent Abilities of Language Models from the Loss Perspective (NeurIPS 2024 · similarity 0.88)
- Unsupervised Translation of Emergent Communication (AAAI 2025 · similarity 0.88)
- Bridging semantics and pragmatics in information-theoretic emergent communication (NeurIPS 2024 · similarity 0.88)
- A compressive-expressive communication framework for compositional representations (NeurIPS 2025 · similarity 0.86)
- Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication (NeurIPS 2024 · similarity 0.86)
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.