Math Education Digital Shadows for facilitating learning with LLMs: Math performance, anxiety and confidence in simulated students and AIs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914520290557952 |
|---|---|
| author | Esposito, Naomi Tricarico, Anthony Porzio, Luisa Ardebili, Ali Aghazadeh Stella, Massimo |
| author_facet | Esposito, Naomi Tricarico, Anthony Porzio, Luisa Ardebili, Ali Aghazadeh Stella, Massimo |
| contents | To enhance LLMs' impact on math education, we need data on their mathematical prowess and biases across prompts. To fill this gap, we introduce MEDS (Math Education Digital Shadows) as a dataset mapping how large language models reason about and report mathematics across human- and AI-like conditions. MEDS involves 28,000 personas from 14 LLMs (from families like Mistral, Qwen, DeepSeek, Granite, Phi and Grok) shadowing either humans or AI assistants. Each record/shadow includes a set of prompts along with psychological/sociodemographic persona metadata and four types of math tasks: (i) open math interview, (ii) three psychometric tests about math perceptions with explanations, (iii) cognitive networks capturing math attitudes, and (iv) 18 high-school math test questions together with their reasoning and confidence scores. MEDS differs from traditional score-only math benchmarks because it integrates concepts of self-efficacy, math anxiety, and cognitive network science besides math proficiency scores. Data validation shows that the sampled LLMs exhibit schema integrity and consistent personas, together with family-specific peculiarities like human-like negative math attitudes, logical fallacies, and math overconfidence. MEDS will benefit learning analytics experts, cognitive scientists, and developers of safer AI tutors in mathematics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27618 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Math Education Digital Shadows for facilitating learning with LLMs: Math performance, anxiety and confidence in simulated students and AIs Esposito, Naomi Tricarico, Anthony Porzio, Luisa Ardebili, Ali Aghazadeh Stella, Massimo Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning Social and Information Networks To enhance LLMs' impact on math education, we need data on their mathematical prowess and biases across prompts. To fill this gap, we introduce MEDS (Math Education Digital Shadows) as a dataset mapping how large language models reason about and report mathematics across human- and AI-like conditions. MEDS involves 28,000 personas from 14 LLMs (from families like Mistral, Qwen, DeepSeek, Granite, Phi and Grok) shadowing either humans or AI assistants. Each record/shadow includes a set of prompts along with psychological/sociodemographic persona metadata and four types of math tasks: (i) open math interview, (ii) three psychometric tests about math perceptions with explanations, (iii) cognitive networks capturing math attitudes, and (iv) 18 high-school math test questions together with their reasoning and confidence scores. MEDS differs from traditional score-only math benchmarks because it integrates concepts of self-efficacy, math anxiety, and cognitive network science besides math proficiency scores. Data validation shows that the sampled LLMs exhibit schema integrity and consistent personas, together with family-specific peculiarities like human-like negative math attitudes, logical fallacies, and math overconfidence. MEDS will benefit learning analytics experts, cognitive scientists, and developers of safer AI tutors in mathematics. |
| title | Math Education Digital Shadows for facilitating learning with LLMs: Math performance, anxiety and confidence in simulated students and AIs |
| topic | Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2604.27618 |