Ontology-constrained multi-LLM scoring of hypothesis support in the predictive processing literature

Fragmentation is common in interdisciplinary fields with diverse methods and theoretical commitments. Predictive coding neuroscience is a clear example: its literature spans computational theory, electrophysiology, imaging, behavior, and modeling, creating a synthesis problem that conventional meta-analysis cannot easily resolve. Here, we describe a local multi-LLM pipeline for ontology-constrained literature synthesis.

The pipeline reads papers, extracts evidence, incorporates figure descriptions, assembles constrained prompts, and validates outputs against an expert glossary. We defined a predictive-coding glossary of thirty-six concepts grouped into three hypotheses: predictive suppression, feedforward error propagation, and ubiquity. A council of ten local language models scored 31 studies across local and global oddball contexts.

This enabled pairwise study-agreement analysis, cross-model comparison, and three-dimensional hypothesis-space mapping. Agreement was stronger for local than global oddball contexts, particularly for feedforward error propagation. Hypothesis-space temperature was lower for local oddball contexts and higher for global oddball contexts, indicating greater dispersion in the latter.

These results show that local multi-LLM councils can produce auditable disagreement measurements that map heterogeneous literatures into quantitative evidence spaces. This research was supported by funding awarded to André M. Bastos from the National Institute of Mental Health R00MH116100 and from the National Science Foundation Career grant 2449277.

Department of Psychology and Vanderbilt Brain Institute, Vanderbilt University, Nashville, US Hamed Nejat, Alexander Maier & André M. Bastos Data Science Institute, Vanderbilt University, Nashville, US Department of Psychology, Vanderbilt University, Nashville, 37240, TN, USA Department of Vision and Cognition, Netherlands Institute for Neuroscience, Royal Netherlands Academy of Arts and Sciences, Amsterdam, 1105 BA, Netherlands The authors declare no competing interests This study analyzed published literature and model-generated outputs only. No new human participant data, human tissue, live vertebrate animal experiments, or clinical intervention data were collected.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it.