大模型
arxiv.org ·
LLM 作为符号回归中生理合理性的事后审计者：一项由临床医生评估的案例研究
该 arXiv 预印本探讨 LLM 能否提升进化计算生成的符号回归模型的可解释性。研究基于此前用语法遗传编程估计体脂率的工作，将 LLM 作为后处理工具，对 4 个演化出的符号表达式进行解释与排序，由 3 个 LLM 各重复 3 次，并由 3 名临床医生评估结果。结果显示，跨模型的比较性排序输出比孤立的项级解释获得更积极的临床评价，但 LLM 也给出了生理学和数学上存疑的解释。作者据此认为，LLM 更适合在专家监督下做比较性审计，而非自主验证。
AI推荐理由 arXiv 预印本，作者与摘要明确，属可验证的学术研究。新信息在于：将 LLM 用作符号回归（遗传编程/语法进化）演化表达式的后处理审计工具，对 4 个符号表达式由 3 个 LLM 各重复 3 次进行解释与排序，并由 3 名临床医生评估。结论具有明确局限：LLM 的比较性排序输出比孤立的项级解释更受临床医生认可，但也会产生生理学和数学上可疑的解释，因此更适合在专家监督下做比较性审计，而非自主验证。该结论对 AI 辅助科学发现与可解释性工作流有参考价值，但样本量小、属案例研究，且为期刊投稿的扩展版本，尚需同行评审。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.11431 (cs)
[Submitted on 10 Sep 2026]
Title:LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study
Authors:Jorge López-Varela, J. Ignacio Hidalgo, José-Manuel Muñoz, Omar Costilla-Reyes, Esther Maqueda, Jesus Moreno-Fernandez, Tomás González-Vidal, J. Manuel Velasco, Oscar Garnica
View a PDF of the paper titled LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study, by Jorge L\'opez-Varela and J. Ignacio Hidalgo and Jos\'e-Manuel Mu\~noz and Omar Costilla-Reyes and Esther Maqueda and Jesus Moreno-Fernandez and Tom\'as Gonz\'alez-Vidal and J. Manuel Velasco and Oscar Garnica
View PDF
HTML (experimental)
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, can assist in improving the explainability of Symbolic Regression models generated by evolutionary computation methods. Building upon our previous work on estimating body fat percentage using grammar-based Genetic Programming , we investigate the use of LLMs as post-processing tools to analyze and rank evolved expressions according to their interpretability and medical plausibility. Four symbolic expressions are analysed 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.\blfootnote{The present work is an extended version of a paper submitted into a journal.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.11431 [cs.AI]
(or
arXiv:2609.11431v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.11431
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: J. Ignacio Hidalgo [view email]
[v1]
Thu, 10 Sep 2026 12:03:33 UTC (1,747 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study, by Jorge L\'opez-Varela and J. Ignacio Hidalgo and Jos\'e-Manuel Mu\~noz and Omar Costilla-Reyes and Esther Maqueda and Jesus Moreno-Fernandez and Tom\'as Gonz\'alez-Vidal and J. Manuel Velasco and Oscar Garnica
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)