mlsanityData to 7 Oct 2026

Prospects for inconsistency detection using large language models and sheaves

arXiv 2401.16713 ↗First posted 30 Jan 2024cs.CY cs.CL math.ATcited by 10

Not on the map. Why?

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.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 25 of its 96 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

25 of 96 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2022Galactica: A Large Language Model for Sciencecited by 736
  6. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  7. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  8. 2023Fine-tuning Language Models for Factualitycited by 219
  9. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  10. 2023Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4cited by 202
  11. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 90
  12. 2020Sheaf Neural Networkscited by 80
13 more
  1. 2023Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?cited by 62
  2. 2023Disinformation Detection: An Evolving Challenge in the Age of LLMscited by 41
  3. 2023Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Predictioncited by 37
  4. 2023Challenges with unsupervised LLM knowledge discoverycited by 30
  5. 2022Survey on Graph Neural Network Acceleration: An Algorithmic Perspectivecited by 26
  6. 2021LESA: Linguistic Encapsulation and Semantic Amalgamation Based Generalised Claim Detection from Online Contentcited by 22
  7. 2023Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?cited by 12
  8. 2021Sheaves as a Framework for Understanding and Interpreting Model Fitcited by 5
  9. 2022Diffusion of Information on Networked Lattices by Gossipcited by 4
  10. 2018A Sheaf Model of Contradictions and Disagreements. Preliminary Report and Discussioncited by 2
  11. 2016Maximal Sections of Sheaves of Data over an Abstract Simplicial Complexcited by 1
  12. 2020Topological Differential Testingcited by 1
  13. 2020Sheaf-theoretic framework for optimal network controlcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 1.

10 papers.

  1. 2025Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Expertscited by 7
  2. 2024Privacy Policy Analysis through Prompt Engineering for LLMscited by 6
  3. 2024Quantum-Like Contextuality in Large Language Modelscited by 4
  4. 2025Benchmarking graph construction by large language models for coherence-driven inferencecited by 2
  5. 2025Misleading through Inconsistency: A Benchmark for Political Inconsistencies Detectioncited by 1
  6. 2026SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memorycited by 1
  7. 2025Coherence-driven inference for cybersecuritycited by 0
  8. 2025Automatic coherence-driven inference on argumentscited by 0
  9. 2025LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipelinecited by 0
  10. 2025On Finding Inconsistencies in Documentscited by 0