Papers by Canmiao Zhou
Syntax-Aware Retrieval Augmentation for Neural Symbolic Regression (2025.emnlp-main)
Copied to clipboard
| Challenge: | Symbolic regression is a powerful technique for discovering mathematical expressions that best fit observed data. |
| Approach: | They propose a syntax-aware retrieval-augmented mechanism that leverages syntactic structure of symbolic expressions to perform context-awful retrieval from a pre-constructed token datastore. |
| Outcome: | The proposed method outperforms representative baselines on symbolic regression benchmarks and is validated on multiple symbolic regression datasets. |