Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Can a Hallucinating Model help in Reducing Human "Hallucination"? (2405.00843v1)

Published 1 May 2024 in cs.AI

Abstract: The prevalence of unwarranted beliefs, spanning pseudoscience, logical fallacies, and conspiracy theories, presents substantial societal hurdles and the risk of disseminating misinformation. Utilizing established psychometric assessments, this study explores the capabilities of LLMs vis-a-vis the average human in detecting prevalent logical pitfalls. We undertake a philosophical inquiry, juxtaposing the rationality of humans against that of LLMs. Furthermore, we propose methodologies for harnessing LLMs to counter misconceptions, drawing upon psychological models of persuasion such as cognitive dissonance theory and elaboration likelihood theory. Through this endeavor, we highlight the potential of LLMs as personalized misinformation debunking agents.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Chapter 8 language and rational thought. In Gerd Sommerhoff (ed.), Life, Brain and Consciousness, volume 63 of Advances in Psychology, pp.  199–218. North-Holland, 1990. doi: https://doi.org/10.1016/S0166-4115(08)60256-3. URL https://www.sciencedirect.com/science/article/pii/S0166411508602563.
  2. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
  3. Bo Bennett. Logically fallacious: the ultimate collection of over 300 logical fallacies (Academic Edition). eBookIt. com, 2012.
  4. Central and peripheral routes to persuasion: An individual difference perspective. Journal of personality and social psychology, 51(5):1032, 1986.
  5. Leon Festinger. Cognitive dissonance. Scientific American, 207(4):93–106, 1962.
  6. Boris Gershman. Witchcraft beliefs around the world: An exploratory analysis. PLOS ONE, 17(11):1–19, 11 2022. doi: 10.1371/journal.pone.0276872. URL https://doi.org/10.1371/journal.pone.0276872.
  7. Sven Ove Hansson. Science and pseudo-science. 2008.
  8. Popular epistemically unwarranted beliefs inventory (peubi): A psychometric instrument for assessing paranormal, pseudoscientific and conspiracy beliefs. Applied Cognitive Psychology, 36(6):1260–1276, 2022. doi: https://doi.org/10.1002/acp.4010. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/acp.4010.
  9. A twenty-year survey of science literacy among college undergraduates. Journal of College Science Teaching, 40(4):31–37, 2011.
  10. Logical fallacy detection. arXiv preprint arXiv:2202.13758, 2022.
  11. Daniel Kahneman. A perspective on judgment and choice: Mapping bounded rationality. Progress in Psychological Science around the World. Volume 1 Neural, Cognitive and Developmental Issues., pp.  1–47, 2013.
  12. Psychological testing: Principles, applications, and issues. Wadsworth/Thomson Learning, 2001.
  13. Benchmarking cognitive biases in large language models as evaluators. arXiv preprint arXiv:2309.17012, 2023.
  14. Ziva Kunda. The case for motivated reasoning. Psychological bulletin, 108(3):480, 1990.
  15. When llms meet cunning questions: A fallacy understanding benchmark for large language models. arXiv preprint arXiv:2402.11100, 2024.
  16. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110, 2022.
  17. Ddl unlimited: Dynamic doxastic logic for introspective agents. Erkenntnis, 50:353–385, 1999. URL https://api.semanticscholar.org/CorpusID:116984078.
  18. Evaluating the logical reasoning ability of chatgpt and gpt-4. arXiv preprint arXiv:2304.03439, 2023.
  19. Examining the relationship between conspiracy theories, paranormal beliefs, and pseudoscience acceptance among a university population. Applied Cognitive Psychology, 28(5):617–625, 2014.
  20. What makes weird beliefs thrive? the epidemiology of pseudoscience. Philosophical Psychology, 28(8):1177–1198, 2015. doi: 10.1080/09515089.2014.971946. URL https://doi.org/10.1080/09515089.2014.971946.
  21. Dissociating language and thought in large language models: a cognitive perspective. arXiv preprint arXiv:2301.06627, 2023.
  22. How susceptible are llms to logical fallacies? arXiv preprint arXiv:2308.09853, 2023.
  23. Constructive modelings for theory change. Notre Dame Journal of Formal Logic, 36(1):120–133, 1995.
  24. David B Resnik. A pragmatic approach to the demarcation problem. Studies in History and Philosophy of Science Part A, 31(2):249–267, 2000.
  25. An examination of the underlying dimensional structure of three domains of contaminated mindware: Paranormal beliefs, conspiracy beliefs, and anti-science attitudes. Thinking & Reasoning, 27(2):187–211, 2021.
  26. Creating a large language model of a philosopher. Mind & Language, 2023.
  27. Raymond M Smullyan. Logicians who reason about themselves. In Theoretical aspects of reasoning about knowledge, pp.  341–352. Elsevier, 1986.
  28. The rationality quotient: Toward a test of rational thinking. MIT press, 2016.
  29. Epistemology. 2005.
  30. Classical mechanics, volume 1. Springer, 2005.
  31. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023.
  32. Causal illusion as a cognitive basis of pseudoscientific beliefs. British Journal of Psychology, 111(4):840–852, 2020. doi: https://doi.org/10.1111/bjop.12441. URL https://bpspsychub.onlinelibrary.wiley.com/doi/abs/10.1111/bjop.12441.
  33. A validation of the pseudoscience endorsement scale and assessment of the cognitive correlates of pseudoscientific beliefs. Humanities and Social Sciences Communications, 10(1):176, Apr 2023. ISSN 2662-9992. doi: 10.1057/s41599-023-01681-3. URL https://doi.org/10.1057/s41599-023-01681-3.
  34. Kevin Waymire. Making Sense of the Nonsensical: A Nuanced Approach to Unwarranted Beliefs and their Holders. PhD thesis, 2019.
  35. Belief formation, organization, and change: Cognitive and motivational influences. The handbook of attitudes, 273:322, 2005.
  36. Jianqiiu Zhang. Should we fear large language models? a structural analysis of the human reasoning system for elucidating llm capabilities and risks through the lens of heidegger’s philosophy. arXiv preprint arXiv:2403.03288, 2024.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Sowmya S Sundaram (8 papers)
  2. Balaji Alwar (1 paper)