Research map / Architectures and efficiency / RNNs and normalization
Compositional Generalization by Learning Analytical Expressions
Qian Liu, Shengnan An, Jian-Guang Lou, Bei Chen, Zeqi Lin, Yan Gao, Bin Zhou, Nanning Zheng, Dongmei Zhang
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 Composer module (vs tree-to-sequence degeneration) (ablation) | LAnE · SCAN Add Jump | accuracy: 0.0 -> 100.0 | Improved |
| add Composer module (ablation) | LAnE · SCAN Length | accuracy: 11.1 -> 100.0 | Improved |
| add Composer module (ablation) | LAnE · SCAN MCD1 | accuracy: 5.3 -> 100.0 | Improved |
| add curriculum learning by input length (ablation) | LAnE · all SCAN tasks | accuracy: 0.0 -> 100.0 | Improved |
| add simplicity-based reward to similarity reward (ablation) | LAnE · SCAN Around Right | accuracy: 0.0 -> 100.0 | Improved |
| add simplicity-based reward to similarity reward (ablation) | LAnE · SCAN MCD3 | accuracy: 78.8 -> 100.0 | Improved |
| add simplicity-based reward to similarity reward (ablation) | LAnE · SCAN Add Jump, Length, MCD1, MCD2 | accuracy: 100.0 -> 100.0 | No clear effect |
| use differential learning rates for Composer and Solver (vs other combinations) (ablation) | LAnE · SCAN | train/test accuracy | Improved |
Closest papers by meaning
- When does compositional structure yield compositional generalization? A kernel theory. (ICLR 2025 · similarity 0.91)
- CraftFactory: A Conditioned Control Policy Benchmark for Compositional Generalization (AAAI 2025 · similarity 0.90)
- Scaling can lead to compositional generalization (NeurIPS 2025 · similarity 0.89)
- Assign and Add: A Mechanistic Study of Compositional Arithmetic (NeurIPS 2026 · similarity 0.88)
- Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning (ICLR 2026 · similarity 0.88)
- Compositional Reasoning in Language Models under Reinforcement Learning Post-Training (NeurIPS 2026 · similarity 0.88)
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.
