# Automatic coherence-driven inference on arguments

arXiv: https://arxiv.org/abs/2509.18523 · HTML: https://mlsanity.com/paper/2509.18523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 86 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On the Existence of Simpler Machine Learning Models](https://mlsanity.com/paper/1908.01755/) (2019)
- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Spectral Sparsification of Hypergraphs](https://mlsanity.com/paper/1807.04974/) (2018)
- [Prospects for inconsistency detection using large language models and sheaves](https://mlsanity.com/paper/2401.16713/) (2024)
- [NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documents](https://mlsanity.com/paper/2412.20602/) (2024)
- [Benchmarking graph construction by large language models for coherence-driven inference](https://mlsanity.com/paper/2502.13953/) (2025)

## Abstract (arXiv)

Inconsistencies are ubiquitous in law, administration, and jurisprudence. Though a cure is too much to hope for, we propose a technological remedy. Large language models (LLMs) can accurately extract propositions from arguments and compile them into natural data structures that enable coherence-driven inference (CDI) via combinatorial optimization. This neurosymbolic architecture naturally separates concerns and enables meaningful judgments about the coherence of arguments that can inform legislative and policy analysis and legal reasoning.