Research map / Large language models / Language, safety and interpretability
Early Syntactic Bootstrapping in an Incremental Memory-Limited Word Learner
Sepideh Sadeghi, Matthias Scheutz
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 |
|---|---|---|---|
| add joint word order learning (M-WO) (ablation) | M-B · D1-D3 early trials | mean word acquisition score | Hurt |
| add joint word order learning (M-WO) (ablation) | M-B · D1-D3 moderate data | mean word acquisition score | Improved |
| add joint word order learning (M-WO) (ablation) | M-B · D1-D3 late trials | mean word acquisition score | No clear effect |
| add joint word order learning (M-WO) (ablation) | M-B · One-shot D4-D6 | acquisition score | Improved |
| add joint word order learning (M-WO) (ablation) | M-B · D3 intention inference | intention accuracy | Mixed |
| add joint word order learning (M-WO) (ablation) | M-B · D6 intention inference | mean accuracy | Improved |
| higher linguistic (D2) or visual (D3) ambiguity vs D1 | M-B · D1-D3 word order learning | word order probability | Hurt |
Closest papers by meaning
- Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs (ICLR 2024 · similarity 0.86)
- A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention (NeurIPS 2024 · similarity 0.84)
- Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models (NeurIPS 2025 · similarity 0.84)
- Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale (NeurIPS 2025 · similarity 0.84)
- A Polar coordinate system represents syntax in large language models (NeurIPS 2024 · similarity 0.83)
- Evaluating the Zero-shot Robustness of Instruction-tuned Language Models (ICLR 2024 · similarity 0.83)
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.
