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

arXiv: https://arxiv.org/abs/2606.05206 · HTML: https://mlsanity.com/paper/2606.05206/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 84 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 19 of 19)

- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [Microscaling Data Formats for Deep Learning](https://mlsanity.com/paper/2310.10537/) (2023)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Dendritic cortical microcircuits approximate the backpropagation algorithm](https://mlsanity.com/paper/1810.11393/) (2018)
- [Large language models surpass human experts in predicting neuroscience results](https://mlsanity.com/paper/2403.03230/) (2024)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [Evaluating Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2512.15567/) (2025)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (2025)
- [The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems](https://mlsanity.com/paper/2509.08713/) (2025)
- [Single-phase deep learning in cortico-cortical networks](https://mlsanity.com/paper/2206.11769/) (2022)
- [Dendritic predictive coding: A theory of cortical computation with spiking neurons](https://mlsanity.com/paper/2205.05303/) (2022)
- [Biases in the Blind Spot: Detecting What LLMs Fail to Mention](https://mlsanity.com/paper/2602.10117/) (2026)
- [Transforming Evidence Synthesis: A Systematic Review of the Evolution of Automated Meta-Analysis in the Age of AI](https://mlsanity.com/paper/2504.20113/) (2025)
- [Revealing Hidden Bias in AI: Lessons from Large Language Models](https://mlsanity.com/paper/2410.16927/) (2024)
- [Neural mechanisms of predictive processing: a collaborative community experiment through the OpenScope program](https://mlsanity.com/paper/2504.09614/) (2025)

## Abstract (arXiv)

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 manually 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 according to their agreement or disagreement with each glossary factor across local and global oddball contexts. This enabled pairwise study-agreement analysis, cross-model comparison, and three-dimensional hypothesis-space mapping. Agreement was high for some hypotheses but weaker for others, revealing structured disagreement, particularly across local versus global oddball paradigms. We further define hypothesis-space temperature, a geometric dispersion metric measuring how compactly studies occupy the hypothesis space. Temperature was lower for local oddball contexts and higher for global oddball contexts, indicating greater dispersion in the latter. The scoring geometry also allowed us to estimate vectors of change between experimental contexts. These results demonstrate that local multi-LLM councils can produce auditable disagreement measurements that map heterogeneous literatures into quantitative evidence spaces. This framework may generalize to cross-study hypothesis mapping where conventional meta-analysis lacks a common comparison space.