# Prospects for inconsistency detection using large language models and sheaves

arXiv: https://arxiv.org/abs/2401.16713 · HTML: https://mlsanity.com/paper/2401.16713/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 96 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [Evaluating the Factual Consistency of Large Language Models Through News Summarization](https://mlsanity.com/paper/2211.08412/) (2022)
- [Sheaf Neural Networks](https://mlsanity.com/paper/2012.06333/) (2020)
- [Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?](https://mlsanity.com/paper/2312.03729/) (2023)
- [Disinformation Detection: An Evolving Challenge in the Age of LLMs](https://mlsanity.com/paper/2309.15847/) (2023)
- [Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction](https://mlsanity.com/paper/2307.08321/) (2023)
- [Challenges with unsupervised LLM knowledge discovery](https://mlsanity.com/paper/2312.10029/) (2023)
- [Survey on Graph Neural Network Acceleration: An Algorithmic Perspective](https://mlsanity.com/paper/2202.04822/) (2022)
- [LESA: Linguistic Encapsulation and Semantic Amalgamation Based Generalised Claim Detection from Online Content](https://mlsanity.com/paper/2101.11891/) (2021)
- [Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?](https://mlsanity.com/paper/2310.14880/) (2023)
- [Sheaves as a Framework for Understanding and Interpreting Model Fit](https://mlsanity.com/paper/2105.10414/) (2021)
- [Diffusion of Information on Networked Lattices by Gossip](https://mlsanity.com/paper/2204.00167/) (2022)
- [A Sheaf Model of Contradictions and Disagreements. Preliminary Report and Discussion](https://mlsanity.com/paper/1801.09036/) (2018)
- [Maximal Sections of Sheaves of Data over an Abstract Simplicial Complex](https://mlsanity.com/paper/1612.00397/) (2016)
- [Topological Differential Testing](https://mlsanity.com/paper/2003.00976/) (2020)
- [Sheaf-theoretic framework for optimal network control](https://mlsanity.com/paper/2012.00120/) (2020)

## Built on by (most cited first, 10 of 10)

- [Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Experts](https://mlsanity.com/paper/2502.13577/) (2025)
- [Privacy Policy Analysis through Prompt Engineering for LLMs](https://mlsanity.com/paper/2409.14879/) (2024)
- [Quantum-Like Contextuality in Large Language Models](https://mlsanity.com/paper/2412.16806/) (2024)
- [Benchmarking graph construction by large language models for coherence-driven inference](https://mlsanity.com/paper/2502.13953/) (2025)
- [Misleading through Inconsistency: A Benchmark for Political Inconsistencies Detection](https://mlsanity.com/paper/2505.19191/) (2025)
- [SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory](https://mlsanity.com/paper/2603.14588/) (2026)
- [Coherence-driven inference for cybersecurity](https://mlsanity.com/paper/2509.18520/) (2025)
- [Automatic coherence-driven inference on arguments](https://mlsanity.com/paper/2509.18523/) (2025)
- [LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipeline](https://mlsanity.com/paper/2512.07867/) (2025)
- [On Finding Inconsistencies in Documents](https://mlsanity.com/paper/2512.18601/) (2025)

## Abstract (arXiv)

We demonstrate that large language models can produce reasonable numerical ratings of the logical consistency of claims. We also outline a mathematical approach based on sheaf theory for lifting such ratings to hypertexts such as laws, jurisprudence, and social media and evaluating their consistency globally. This approach is a promising avenue to increasing consistency in and of government, as well as to combating mis- and disinformation and related ills.