Metraipolis › archive › dc_d21531347e34
Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights — arXiv:2609.08797
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08797
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:58:20.718Z
- SHA-256 of the archived text
1afdda10d677c2c5bd82360787c56a4e2bb0a621a635cae77097601cb4bb8b83- Stable URL of this page
https://metraipolis.com/documento/dc_d21531347e34
How to cite
Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights — arXiv:2609.08797 — arXiv (en), https://arxiv.org/abs/2609.08797 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d21531347e34 (Metraipolis archive dc_d21531347e34, sha256 1afdda10d677c2c5bd82360787c56a4e2bb0a621a635cae77097601cb4bb8b83)
BibTeX
@misc{dcd21531347e34,
title = {Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights — arXiv:2609.08797},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08797},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d21531347e34; sha256 1afdda10d677c2c5bd82360787c56a4e2bb0a621a635cae77097601cb4bb8b83},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08797. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pairs of ratings and category labels, with weights derived from LLM embeddings. The model does not presuppose ordered category thresholds or equidistant scoring; instead, it focuses on pairwise agreement among ratings and assigns category-specific positive weights, making it suited for multi-category scoring reliability. We evaluate the model on three constructed-response datasets spanning a corpus of K=14,466 short answers on a three-level rubric and two AERA essay prompts of roughly 1,200-1,400 responses on four-point rubrics. We compare three strategies for sharpening the similarity signal: top-K pruning, min-max normalization with a power transformation, and ColBERT late-interaction similarities. Top-K pruning, which replaces the dense similarity graph with a sparse local network of strongest semantic neighbors, consistently yields the highest accuracy and Cohen's kappa, and the selected neighborhoods are always a small fraction of the corpus. Power tuning consistently ranks second, while ColBERT is competitive on longer essay prompts and adds little on short answers. Across all settings, most misclassifications occur between adjacent score levels, confirming that the model preserves the ordinal structure of scoring rubrics without imposing rigid assumptions. These findings suggest that LLM-derived similarities, combined with a parsimonious Potts formulation and a sparse local graph, offer a robust and interpretable framework for reliability auditing in educational assessment. We discuss extensions to multiple raters and hierarchical rating designs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Applications (stat.AP) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.08797 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T12:30:25.365Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).