aiqbench analysis
This research investigates whether the "bullshit" language characteristics of ChatGPT can be statistically modeled and linked to real-world political and workplace dysfunction, offering a novel lens on LLM linguistic behavior beyond standard safety metrics. By contrasting model-generated text with scientific literature, the study provides empirical evidence that current generative AI systems may inadvertently replicate patterns associated with social incoherence and obfuscation.
The BS-meter: Detecting Politics and Labour through ChatGPT's Language
arXiv:2411.15129v3 Announce Type: replace-cross Abstract: What can we learn about language from studying how it is used by ChatGPT and other large language model (LLM)-based chatbots? In this paper, we analyse the distinctive character of language generated by ChatGPT, in relation to questions raised by natural language processing pioneer, and student of Wittgenstein, Margaret Masterman. Following frequent complaints that LLM-based chatbots produce "bullshit," in the sense of Frankfurt's popular monograph On Bullshit, we conduct an empirical study to contrast the language of 1,000 scientific publications with typical text generated by ChatGPT. We then explore whether the same language features can be detected in two well-known contexts of social dysfunction: George Orwell's critique of political speech, and David Graeber's characterisation of bullshit jobs. Using simple hypothesis-testing methods, we demonstrate that a statistical model of bullshit can reliably relate the Frankfurtian artificial bullshit of ChatGPT to the political and workplace functions of bullshit as observed in natural human language.
Abstract:What can we learn about language from studying how it is used by ChatGPT and other large language model (LLM)-based chatbots? In this paper, we analyse the distinctive character of language generated by ChatGPT, in relation to questions raised by natural language processing pioneer, and student of Wittgenstein, Margaret Masterman. Following frequent complaints that LLM-based chatbots produce "bullshit," in the sense of Frankfurt's popular monograph On Bullshit, we conduct an empirical study to contrast the language of 1,000 scientific publications with typical text generated by ChatGPT. We then explore whether the same language features can be detected in two well-known contexts of social dysfunction: George Orwell's critique of political speech, and David Graeber's characterisation of bullshit jobs. Using simple hypothesis-testing methods, we demonstrate that a statistical model of bullshit can reliably relate the Frankfurtian artificial bullshit of ChatGPT to the political and workplace functions of bullshit as observed in natural human language.
17 pages, 5 figures. Accepted for publication in AI&SOCIETY
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
arXiv:2411.15129 [cs.CL]
(or arXiv:2411.15129v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2411.15129 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 260 words
