How AI Systems Think About Education: Analyzing Latent Preference Patterns in Large Language Models
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914413464780800 |
|---|---|
| author | Autenrieth, Daniel |
| author_facet | Autenrieth, Daniel |
| contents | This paper presents the first systematic measurement of educational alignment in Large Language Models. Using a Delphi-validated instrument comprising 48 items across eight educational-theoretical dimensions, the study reveals that GPT-5.1 exhibits highly coherent preference patterns (99.78% transitivity; 92.79% model accuracy) that largely align with humanistic educational principles where expert consensus exists. Crucially, divergences from expert opinion occur precisely in domains of normative disagreement among human experts themselves, particularly emotional dimensions and epistemic normativity. This raises a fundamental question for alignment research: When human values are contested, what should models be aligned to? The findings demonstrate that GPT-5.1 does not remain neutral in contested domains but adopts coherent positions, prioritizing emotional responsiveness and rejecting false balance. The methodology, combining Delphi consensus-building with Structured Preference Elicitation and Thurstonian Utility modeling, provides a replicable framework for domain-specific alignment evaluation beyond generic value benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21006 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How AI Systems Think About Education: Analyzing Latent Preference Patterns in Large Language Models Autenrieth, Daniel Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction I.2.7; K.3.1 This paper presents the first systematic measurement of educational alignment in Large Language Models. Using a Delphi-validated instrument comprising 48 items across eight educational-theoretical dimensions, the study reveals that GPT-5.1 exhibits highly coherent preference patterns (99.78% transitivity; 92.79% model accuracy) that largely align with humanistic educational principles where expert consensus exists. Crucially, divergences from expert opinion occur precisely in domains of normative disagreement among human experts themselves, particularly emotional dimensions and epistemic normativity. This raises a fundamental question for alignment research: When human values are contested, what should models be aligned to? The findings demonstrate that GPT-5.1 does not remain neutral in contested domains but adopts coherent positions, prioritizing emotional responsiveness and rejecting false balance. The methodology, combining Delphi consensus-building with Structured Preference Elicitation and Thurstonian Utility modeling, provides a replicable framework for domain-specific alignment evaluation beyond generic value benchmarks. |
| title | How AI Systems Think About Education: Analyzing Latent Preference Patterns in Large Language Models |
| topic | Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction I.2.7; K.3.1 |
| url | https://arxiv.org/abs/2603.21006 |