# LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study

DevFeed: [LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study](<https://devfeed.tech/articles/llms-as-post-hoc-auditors-of-physiological-plausibility-in-symbolic-regression-a-clinician-evaluated-case-study-124476.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.11431>)

Author: Jorge L\\'opez-Varela, J. Ignacio Hidalgo, Jos\\'e-Manuel Mu\\~noz, Omar Costilla-Reyes, Esther Maqueda, Jesus Moreno-Fernandez, Tom\\'as Gonz\\'alez-Vidal, J. Manuel Velasco, Oscar Garnica

Published: 2026-11-09T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [auditing](<https://devfeed.tech/tags/auditing.md>), [autonomous-validation](<https://devfeed.tech/tags/autonomous-validation.md>), [body](<https://devfeed.tech/tags/body.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [interpretability](<https://devfeed.tech/tags/interpretability.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llms](<https://devfeed.tech/tags/llms.md>), [rank](<https://devfeed.tech/tags/rank.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [regression](<https://devfeed.tech/tags/regression.md>), [symbolic-regression](<https://devfeed.tech/tags/symbolic-regression.md>)

## AI overview

Three LLMs evaluated four symbolic regression expressions for body-fat estimation across three repeated runs, with three clinicians assessing their interpretations and rankings. Clinicians viewed comparative rankings more favorably than explanations of individual terms, but the LLMs also gave physiologically or mathematically questionable explanations. The findings support using LLMs for comparative plausibility audits under clinician oversight, not autonomous validation.

## Source excerpt

arXiv:2609.11431v2 Announce Type: replace Abstract: Genetic programming and its variants, such as grammatical evolution, are widely used in symbolic regression to derive mathematical expressions from multivariate data. In addition to predictive accuracy, models are appreciated for their potential to provide interpretability, offering explicit equations that relate input variables to outcomes. However, achieving interpretability and plausibility remains challenging, as evolved models may be complex or scientifically inconsistent. In this study, we explore whether large language models (LLMs) can assist in improving the interpretability of symbolic regression models generated by evolutionary computation methods. Building on our previous work on estimating body fat percentage using grammar-based genetic programming, we investigate LLMs as post-processing tools to analyze and rank evolved expressions by interpretability and physiological plausibility. Four symbolic expressions are analyzed by three LLMs over three repeated runs, and the resulting interpretations and rankings are assessed by a panel of three clinicians. Across the three LLMs, comparative model-ranking outputs received more favorable clinician assessments than isolated term-level interpretations. However, the LLMs also produced physiologically and mathematically questionable explanations, indicating that they are better suited to comparative auditing under expert oversight than to autonomous validation.