Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben
Erschienen in:
Network Design Through Graph Neural Networks: Identifying Challenges and Improving Performance Kapitel lesen Erstes Kapitel lesen

2024 | OriginalPaper | Buchkapitel

Untangling Emotional Threads: Hallucination Networks of Large Language Models

verfasst von : Mahsa Goodarzi, Radhakrishnan Venkatakrishnan, M. Abdullah Canbaz

Erschienen in: Complex Networks & Their Applications XII

Verlag: Springer Nature Switzerland

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Generative AI models, known for their capacity to generate intricate and realistic data, have rapidly found applications across various domains. Yet, doubts linger regarding the full scope of their hallucinatory capabilities and the reliability of their outcomes. These concerns underscore the need for rigorous analysis and validation of generative AI models. This study employs network analysis to explore the inherent characteristics of generative AI models, focusing on their deviations and disparities between generated and actual content. Using GPT3.5 and RoBERTa, we analyze tweets, vocabulary, and emotion networks from their outputs. Although network comparison demonstrated hallucination, non-classification, and instability patterns in GPT-3.5 compared to RoBERTa as a baseline, both models exhibit promise and room for improvement.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren
Vorheriges Kapitel Economic and Health Burdens of HIV and COVID-19: Insights from a Survey of Underserved Communities in Semi-Urban and Rural Illinois
Nächstes Kapitel Analyzing Trendy Twitter Hashtags in the 2022 French Election
Literatur
1.
2.
Acheampong, F.A., Nunoo-Mensah, H., Chen, W.: Transformer models for text-based emotion detection: a review of BERT-based approaches (2021)
3.
Alkaissi, H., McFarlane, S.I.: Artificial hallucinations in chatgpt: implications in scientific writing. Cureus (2023)
4.
Amidi, F.: Hashtags, a viral song and memes empower iran’s protesters (2022)
5.
Athaluri, S.A., Manthena, S.V. Kesapragada, V.S.R., Yarlagadda, V., Dave, T., Duddumpudi, R.T.S.: Exploring the boundaries of reality: investigating the phenomenon of artificial intelligence hallucination in scientific writing through chatgpt references (2023)
6.
Bar-Kalifa, E., Sened, H.: Using network analysis for examining interpersonal emotion dynamics. Multivariate Behav. Res. (2020)
7.
Barnes, J.: Twitter ends its free API: Here’s who will be affected
8.
Bird, S., Klein, E., Loper, E.: Natural language processing with Python. O’Reilly (2009)
9.
Biswas, S.S.: Potential use of chat gpt in global warming. Annals Biomed. Eng. (2023)
10.
Blondel, V.D., Guillaume, J.-L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks (2008)
11.
Camacho-Collados, J., et al.: TweetNLP: Cutting-Edge Natural Language Processing for Social Media (2022)
12.
Cowen, A.S., Keltner, D.: Self-report captures 27 distinct categories of emotion bridged by continuous gradients. Proc. Nat. Acad. Sci. (2017)
13.
Davis, W.: Twitter is being rebranded as x - the verge (2023)
14.
Fuchs, K.: Exploring the opportunities and challenges of nlp models in higher education: is chat gpt a blessing or a curse? (2023)
15.
16.
Hasmi, L., et al.: Network approach to understanding emotion dynamics in relation to childhood trauma and genetic liability to psychopathology: replication of a prospective experience sampling analysis (2017)
17.
Huang, F., Kwak, H., An, J.: Is chatgpt better than human annotators? potential and limitations of chatgpt in explaining implicit hate speech. arXiv:​2302.​07736 (2023)
18.
Johnson, D., Goodman, R., Patrinely, J., Stone, C., Zimmerman, E., et al.: Assessing the accuracy and reliability of ai-generated medical responses: an evaluation of the chat-gpt model (2023)
19.
Kinnison, J., Padmala, S., Choi, J-M., Pessoa, L.: Network analysis reveals increased integration during emotional and motivational processing. J. Neurosci. (2012)
20.
Lange, J., Zickfeld, J.H.: Emotions as overlapping causal networks of emotion components: implications and methodological approaches (2021)
21.
Liang, S., et al.: The relations between emotion regulation, depression and anxiety among medical staff during the late stage of covid-19 pandemic: a network analysis. Psych. Res. (2022)
22.
Loureiro, D., et al.: Tweet insights: a visualization platform to extract temporal insights from twitter arXiv:​2308.​02142 (2023)
23.
Martín-Brufau, R., Suso-Ribera, C., Corbalán, J.: Emotion network analysis during covid-19 quarantine-a longitudinal study. Front. Psychol. (2020)
24.
Matsumoto, D., Keltner, D., Shiota, M.N., O’Sullivan, M., Frank, M.: Facial expressions of emotion (2008)
25.
Mauss, I.B., Levenson, R.W., McCarter, L., Wilhelm, F.H., Gross, J.J.: The tie that binds? coherence among emotion experience, behavior, and physiology (2005)
26.
Ouyang, L., et al.: Training language models to follow instructions with human feedback (2022)
27.
Parrott, W.G.: Emotions in social psychology: Essential readings. Psychology Press (2001)
28.
Pessoa, L.: Understanding emotion with brain networks. Current Opinion Behav. Sci. (2018)
29.
Rudolph, J., Tan, S., Tan, S.: Chatgpt: bullshit spewer or the end of traditional assessments in higher education? J. Appl. Learn. Teach. (2023)
30.
Sailunaz, K., Alhajj, R.: Emotion and sentiment analysis from twitter text. J. Comput. Sci. (2019)
31.
Si, C., et al.: Prompting GPT-3 to be reliable (2023)
32.
Siegel, E.H., et al.: Emotion fingerprints or emotion populations? a meta-analytic investigation of autonomic features of emotion categories (2018)
33.
Sohail, S.S., et al.: Decoding chatgpt: A taxonomy of existing research, current challenges, and possible future directions (2023)
34.
Tantardini, M., Ieva, F., Tajoli, L., Piccardi, C.: Comparing methods for comparing networks. 9, 17557 (2019)
35.
Trampe, D., Quoidbach, J., Taquet, M.: Emotions in everyday life. PloS one (2015)
36.
Tunstall, L., von Werra, L., Wolf, T.: Natural language processing with transformers: building language applications with Hugging Face (2022)
37.
Vaira, L.A., et al.: Accuracy of chatgpt-generated information on head and neck and oromaxillofacial surgery: a multicenter collaborative analysis (2023)
38.
Vaswani, A., et al.: Attention is all you need (2017)
39.
Venkatakrishnan, R., Goodarzi, M.,Canbaz, M.A.: Use cases from the middle east, Exploring large language models’ emotion detection abilities (2023)
40.
Witkower, Z., Tracy, J.L.: A facial-action imposter: How head tilt influences perceptions of dominance from a neutral face (2019)
Metadaten
Titel
Untangling Emotional Threads: Hallucination Networks of Large Language Models
verfasst von
Mahsa Goodarzi
Radhakrishnan Venkatakrishnan
M. Abdullah Canbaz
Copyright-Jahr
2024
Buch
Complex Networks & Their Applications XII

Print ISBN: 978-3-031-53467-6

Electronic ISBN: 978-3-031-53468-3

Copyright-Jahr: 2024

DOI
https://doi.org/10.1007/978-3-031-53468-3_17

Premium Partner

    Bildnachweise