mlsanityData to 7 Oct 2026

Consistency Analysis of ChatGPT

arXiv 2303.06273 ↗First posted 11 Mar 2023cs.CL cs.AIcited by 37

Not on the map. Why?

Abstract (arXiv)

ChatGPT has gained a huge popularity since its introduction. Its positive aspects have been reported through many media platforms, and some analyses even showed that ChatGPT achieved a decent grade in professional exams, adding extra support to the claim that AI can now assist and even replace humans in industrial fields. Others, however, doubt its reliability and trustworthiness. This paper investigates the trustworthiness of ChatGPT and GPT-4 regarding logically consistent behaviour, focusing specifically on semantic consistency and the properties of negation, symmetric, and transitive consistency. Our findings suggest that while both models appear to show an enhanced language understanding and reasoning ability, they still frequently fall short of generating logically consistent predictions. We also ascertain via experiments that prompt designing, few-shot learning and employing larger large language models (LLMs) are unlikely to be the ultimate solution to resolve the inconsistency issue of LLMs.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 27 of its 59 references that are in the map. First posted on arXiv 11 Mar 2023.

Builds on

27 of 59 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  8. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  9. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  10. 2019How Can We Know What Language Models Know?cited by 953
  11. 2018WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representationscited by 370
  12. 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 317
15 more
  1. 2023Mathematical Capabilities of ChatGPTcited by 263
  2. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 240
  3. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  4. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 90
  5. 2020Logic-Guided Data Augmentation and Regularization for Consistent Question Answeringcited by 77
  6. 2021Understanding by Understanding Not: Modeling Negation in Language Modelscited by 73
  7. 2019Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanationscited by 71
  8. 2019A Logic-Driven Framework for Consistency of Neural Modelscited by 64
  9. 2021Consistency Regularization for Cross-Lingual Fine-Tuningcited by 41
  10. 2022Measuring Reliability of Large Language Models through Semantic Consistencycited by 38
  11. 2021Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answeringcited by 27
  12. 2018What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Taskscited by 14
  13. 2023Can ChatGPT-like Generative Models Guarantee Factual Accuracy? On the Mistakes of New Generation Search Enginescited by 14
  14. 2022Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondencecited by 10
  15. 2022Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Taskscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 9; 2025: 9; 2026: 5.

37 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  3. 2023ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learningcited by 203
  4. 2023A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasetscited by 123
  5. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  6. 2023Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queriescited by 82
  7. 2024MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notescited by 77
  8. 2023Language models are not naysayers: An analysis of language models on negation benchmarkscited by 73
  9. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
  10. 2023Evaluating Superhuman Models with Consistency Checkscited by 47
  11. 2024Reasoning Runtime Behavior of a Program with LLM: How Far Are We?cited by 44
  12. 2023Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Modelscited by 40
25 more
  1. 2023In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPTcited by 35
  2. 2024Logically Consistent Language Models via Neuro-Symbolic Integrationcited by 30
  3. 2023Separating form and meaning: Using self-consistency to quantify task understanding across multiple sensescited by 15
  4. 2025Prompt-Reverse Inconsistency: LLM Self-Inconsistency Beyond Generative Randomness and Prompt Paraphrasingcited by 14
  5. 2025Consistency in Language Models: Current Landscape, Challenges, and Future Directionscited by 14
  6. 2025Potemkin Understanding in Large Language Modelscited by 14
  7. 2024Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMscited by 11
  8. 2024Scope Ambiguities in Large Language Modelscited by 11
  9. 2023Do You Trust ChatGPT? -- Perceived Credibility of Human and AI-Generated Contentcited by 9
  10. 2025Large Language Models Often Say One Thing and Do Anothercited by 8
  11. 2023Framework-Based Qualitative Analysis of Free Responses of Large Language Models: Algorithmic Fidelitycited by 7
  12. 2023Utilizing ChatGPT to Enhance Clinical Trial Enrollmentcited by 4
  13. 2024Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Taskscited by 4
  14. 2025Automated Consistency Analysis of LLMscited by 4
  15. 2024A Prompt Engineering Approach and a Knowledge Graph based Framework for Tackling Legal Implications of Large Language Model Answerscited by 1
  16. 2024Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answeringcited by 1
  17. 2025Legal Requirements Translation from Lawcited by 1
  18. 2026Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?cited by 1
  19. 2024A Survey on the Real Power of ChatGPTcited by 0
  20. 2025How Good LLM-Generated Password Policies Are?cited by 0
  21. 2025Explainability Through Systematicity: The Hard Systematicity Challenge for Artificial Intelligencecited by 0
  22. 2026ReIn: Conversational Error Recovery with Reasoning Inceptioncited by 0
  23. 2026The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPTcited by 0
  24. 2026Thought without systematicity? Evaluating reasoning models on rule induction taskscited by 0
  25. 2026Segment-Level Agentic Topic Modeling for Improved Data Exploration and Resource Efficiencycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
  2. 2025Existing LLMs Are Not Self-Consistent For Simple Tasks
  3. 2024Testing and Evaluation of Large Language Models: Correctness, Non-Toxicity, and Fairness
  4. 2024When is the consistent prediction likely to be a correct prediction?
  5. 2023Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
  6. 2023On Measuring Faithfulness or Self-consistency of Natural Language Explanations
  7. 2024Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
  8. 2023DetectGPT-SC: Improving Detection of Text Generated by Large Language Models through Self-Consistency with Masked Predictions