LLMs show promise as post-hoc auditors for symbolic regression models

Researchers explored using large language models (LLMs) to audit symbolic regression models for physiological plausibility, particularly in a medical context. While LLMs showed promise in ranking evolved mathematical expressions, their explanations were sometimes physiologically and mathematically questionable. Clinicians found the LLMs' comparative rankings more useful than isolated term interpretations, suggesting LLMs are better suited for expert-supervised auditing rather than autonomous validation. AI

IMPACT LLMs can assist in validating complex scientific models, potentially accelerating discovery in fields like medicine.

RANK_REASON The cluster contains an academic paper detailing a novel research methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• DagsHub
• genetic programming
• grammatical evolution
• Hugging Face
• J. Ignacio Hidalgo
• large-language models
• Symbolic regression

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →