438 research outputs found

    Forged-GAN-BERT: Authorship Attribution for LLM-Generated Forged Novels

    Full text link
    The advancement of generative Large Language Models (LLMs), capable of producing human-like texts, introduces challenges related to the authenticity of the text documents. This requires exploring potential forgery scenarios within the context of authorship attribution, especially in the literary domain. Particularly, two aspects of doubted authorship may arise in novels, as a novel may be imposed by a renowned author or include a copied writing style of a well-known novel. To address these concerns, we introduce Forged-GAN-BERT, a modified GAN-BERT-based model to improve the classification of forged novels in two data-augmentation aspects: via the Forged Novels Generator (i.e., ChatGPT) and the generator in GAN. Compared to other transformer-based models, the proposed Forged-GAN-BERT model demonstrates an improved performance with F1 scores of 0.97 and 0.71 for identifying forged novels in single-author and multi-author classification settings. Additionally, we explore different prompt categories for generating the forged novels to analyse the quality of the generated texts using different similarity distance measures , including ROUGE-1, Jaccard Similarity, Overlap Confident, and Cosine Similarity

    Are BERT-based fact-checking models robust against adversarial attack?

    No full text
    We seek to examine the vulnerability of BERT-based fact-checking. We implement a gradient based, adversarial attack strategy, based on Hotflip swapping individual tokens from the input. We use this on a pre-trained ExPred model for fact-checking. We find that gradient based adversarial attacks are ineffective against ExPred. Uncertainties about the similitude of the examples generated by our adversarial attack implementation cast doubts on the results.https://github.com/somePersone/HotFlip-for-Expred Hotflip implementationCSE3000 Research ProjectComputer Science and Engineerin

    Paired-domination

    No full text

    A weak law of large numbers for m-dependent random variables with unbounded M

    Full text link
    Statistical Methods;mathematische statistiek

    Observing Extremely Dispersive Light in Photonic Crystals and Cavities

    No full text
    We discovered a small mistake in the dataprocessing. Please see or our next output for the corrected version.Developed an interferometric optical reflectivity microscope to observe phase-sensitive reflectivity of nanophotonic structures. High spatial and spectral resolution over broad frequency ranges (750 &lt; λ &lt; 2500 nm). From frequency-resolved phases obtain the (group) time delay. Study planar microcavities (GaAs/AlAs), and Silicon three-dimensional (3D) photonic band gap crystals. For planar microcavity with stopband centred at 1331 nm and a Δω/ω≈16%, we observe time delays τ_g&gt; 4 ps for L = 4.66 μm thickness. For 3D woodpile crystal observe time delays τ_g&gt; 550 fs for L = 780 nm thickness. Combined with the very thin metasurface structure, this yields a lower bound for the group index of n_g≥ 100, much more than previously observed in photonic crystal waveguides. <br/

    Author response

    No full text

    About Tobin's marginal and average q: A note

    Full text link
    Portfolio Management;management science
    corecore