Automatic coherence-driven inference on arguments
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 8 of its 86 references that are in the map. First posted on arXiv 23 Sep 2025.
Builds on
8 of 86 references.
References · 8
- 2017Attention Is All You Needcited by 60,106
- 2019On the Existence of Simpler Machine Learning Modelscited by 88
- 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
- 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
- 2018Spectral Sparsification of Hypergraphscited by 10
- 2024Prospects for inconsistency detection using large language models and sheavescited by 10
- 2024NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documentscited by 4
- 2025Benchmarking graph construction by large language models for coherence-driven inferencecited by 2
Built on by
Not cited yet.