Researchers introduce L2G-SR framework for LLM-based symbolic regression
The paper announces L2G‑SR, a new framework that augments large language model (LLM) driven symbolic regression with a learned structural verifier. The verifier aligns numerical observations with candidate formulas and scores structural similarity using tree edit distance, accounting for commutative operators and alternative expression forms.
Key points
- L2G‑SR adds a learned structural verifier to guide symbolic regression alongside numerical error
- Verifier uses tree edit distance with commutative‑operator handling to score structural similarity
- On LLM‑SRBench, L2G‑SR attains state‑of‑the‑art numerical fit, equation accuracy and TED across tested LLM backbones
During search, the hidden target formula is complemented by the verifier’s feedback, influencing parent selection alongside traditional numerical error. Analysts can inspect verifier diagnostics and guide revisions, which a generator then refines into improved expressions. Evaluation on the LLM‑SRBench suite shows L2G‑SR achieving state‑of‑the‑art numerical fit, equation‑level accuracy and lower tree edit distance across multiple LLM backbones and domains.
The authors argue that learned structural guidance adds valuable signal beyond pure numeric error, helping LLMs discover equations that not only fit data but also match the intended symbolic structure.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- OpenAI offers U.S. university labs free ChatGPT Business seats with Rosalind access · 2 src
- Anthropic reports small AI models may self-replicate on IoT devices within months · 29 src
- Researchers propose LLM-referenced C-test for evaluating supra-intelligence · 8 src
- Researchers study permutation diffusion LLMs for recommendation reranking · 1 src
- Researchers compare Non-Generative verifier to Astra LLM for RAG claim checks · 1 src
Comments
via GitHub Discussions