Charting the Parrot's Song: A Maximum Mean Discrepancy Approach to Measuring AI Novelty, Originality, and Distinctiveness

• URL: http://arxiv.org/abs/2504.08446v1
• Date: Fri, 11 Apr 2025 11:15:26 GMT
• Title: Charting the Parrot's Song: A Maximum Mean Discrepancy Approach to Measuring AI Novelty, Originality, and Distinctiveness
• Authors: Anirban Mukherjee, Hannah Hanwen Chang,
• Abstract summary: This paper introduces a robust, quantitative methodology to measure distributional differences between generative processes.<n>By comparing entire output distributions rather than conducting pairwise similarity checks, our approach directly contrasts creative processes.<n>This research provides courts and policymakers with a computationally efficient, legally relevant tool to quantify AI novelty.
• Score: 0.2209921757303168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current intellectual property frameworks struggle to evaluate the novelty of AI-generated content, relying on subjective assessments ill-suited for comparing effectively infinite AI outputs against prior art. This paper introduces a robust, quantitative methodology grounded in Maximum Mean Discrepancy (MMD) to measure distributional differences between generative processes. By comparing entire output distributions rather than conducting pairwise similarity checks, our approach directly contrasts creative processes--overcoming the computational challenges inherent in evaluating AI outputs against unbounded prior art corpora. Through experiments combining kernel mean embeddings with domain-specific machine learning representations (LeNet-5 for MNIST digits, CLIP for art), we demonstrate exceptional sensitivity: our method distinguishes MNIST digit classes with 95% confidence using just 5-6 samples and differentiates AI-generated art from human art in the AI-ArtBench dataset (n=400 per category; p<0.0001) using as few as 7-10 samples per distribution despite human evaluators' limited discrimination ability (58% accuracy). These findings challenge the "stochastic parrot" hypothesis by providing empirical evidence that AI systems produce outputs from semantically distinct distributions rather than merely replicating training data. Our approach bridges technical capabilities with legal doctrine, offering a pathway to modernize originality assessments while preserving intellectual property law's core objectives. This research provides courts and policymakers with a computationally efficient, legally relevant tool to quantify AI novelty--a critical advancement as AI blurs traditional authorship and inventorship boundaries.

Related papers

• Perceptual Quality Assessment for Embodied AI [66.96928199019129]
  Embodied AI has developed rapidly in recent years, but it is still mainly deployed in laboratories.<n>There is no IQA method to assess the usability of an image in embodied tasks, namely, the perceptual quality for robots.
  arXiv  Detail & Related papers  (2025-05-22T15:51:07Z)
• Behind the Screens: Uncovering Bias in AI-Driven Video Interview Assessments Using Counterfactuals [0.0]
  We introduce a counterfactual-based framework to evaluate and quantify bias in AI-driven personality assessments.<n>Our approach employs generative adversarial networks (GANs) to generate counterfactual representations of job applicants.<n>This work provides a scalable tool for fairness auditing of commercial AI hiring platforms.
  arXiv  Detail & Related papers  (2025-05-17T18:46:14Z)
• A Meaningful Perturbation Metric for Evaluating Explainability Methods [55.09730499143998]
  We introduce a novel approach, which harnesses image generation models to perform targeted perturbation.<n> Specifically, we focus on inpainting only the high-relevance pixels of an input image to modify the model's predictions while preserving image fidelity.<n>This is in contrast to existing approaches, which often produce out-of-distribution modifications, leading to unreliable results.
  arXiv  Detail & Related papers  (2025-04-09T11:46:41Z)
• Detecting Discrepancies Between AI-Generated and Natural Images Using Uncertainty [91.64626435585643]
  We propose a novel approach for detecting AI-generated images by leveraging predictive uncertainty to mitigate misuse and associated risks.<n>The motivation arises from the fundamental assumption regarding the distributional discrepancy between natural and AI-generated images.<n>We propose to leverage large-scale pre-trained models to calculate the uncertainty as the score for detecting AI-generated images.
  arXiv  Detail & Related papers  (2024-12-08T11:32:25Z)
• Learning to Generate and Evaluate Fact-checking Explanations with Transformers [10.970249299147866]
  Research contributes to the field of Explainable Artificial Antelligence (XAI) We develop transformer-based fact-checking models that contextualise and justify their decisions by generating human-accessible explanations. We emphasise the need for aligning Artificial Intelligence (AI)-generated explanations with human judgements.
  arXiv  Detail & Related papers  (2024-10-21T06:22:51Z)
• Psittacines of Innovation? Assessing the True Novelty of AI Creations [0.26107298043931204]
  We task an AI with generating project titles for hypothetical crowdfunding campaigns. We compare within AI-generated project titles, measuring repetition and complexity. Results suggest that the AI generates unique content even under increasing task complexity.
  arXiv  Detail & Related papers  (2024-03-17T13:08:11Z)
• Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attacks [7.500941533148728]
  We propose a cloud-based service framework that encapsulates computing components and assessment tasks into pipelines. We demonstrate the application of XAI services for assessing five quality attributes of AI models.
  arXiv  Detail & Related papers  (2024-01-22T00:37:01Z)
• Precise Benchmarking of Explainable AI Attribution Methods [0.0]
  We propose a novel evaluation approach for benchmarking state-of-the-art XAI attribution methods. Our proposal consists of a synthetic classification model accompanied by its derived ground truth explanations. Our experimental results provide novel insights into the performance of Guided-Backprop and Smoothgrad XAI methods.
  arXiv  Detail & Related papers  (2023-08-06T17:03:32Z)
• An Experimental Investigation into the Evaluation of Explainability Methods [60.54170260771932]
  This work compares 14 different metrics when applied to nine state-of-the-art XAI methods and three dummy methods (e.g., random saliency maps) used as references. Experimental results show which of these metrics produces highly correlated results, indicating potential redundancy.
  arXiv  Detail & Related papers  (2023-05-25T08:07:07Z)
• Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment [66.91538273487379]
  There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. We study how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data.
  arXiv  Detail & Related papers  (2023-02-13T16:44:44Z)
• MAUVE Scores for Generative Models: Theory and Practice [95.86006777961182]
  We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images. We find that MAUVE can quantify the gaps between the distributions of human-written text and those of modern neural language models. We demonstrate in the vision domain that MAUVE can identify known properties of generated images on par with or better than existing metrics.
  arXiv  Detail & Related papers  (2022-12-30T07:37:40Z)
• A Comparative Approach to Explainable Artificial Intelligence Methods in Application to High-Dimensional Electronic Health Records: Examining the Usability of XAI [0.0]
  XAI aims to produce a demonstrative factor of trust, which for human subjects is achieved through communicative means. The ideology behind trusting a machine to tend towards the livelihood of a human poses an ethical conundrum. XAI methods produce visualization of the feature contribution towards a given models output on both a local and global level.
  arXiv  Detail & Related papers  (2021-03-08T18:15:52Z)
• Estimating and Improving Fairness with Adversarial Learning [65.99330614802388]
  We propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system. Specifically, we propose to add a discrimination module against bias and a critical module that predicts unfairness within the base classification model. We evaluate our framework on a large-scale public-available skin lesion dataset.
  arXiv  Detail & Related papers  (2021-03-07T03:10:32Z)
• Fair Meta-Learning For Few-Shot Classification [7.672769260569742]
  A machine learning algorithm trained on biased data tends to make unfair predictions. We propose a novel fair fast-adapted few-shot meta-learning approach that efficiently mitigates biases during meta-train. We empirically demonstrate that our proposed approach efficiently mitigates biases on model output and generalizes both accuracy and fairness to unseen tasks.
  arXiv  Detail & Related papers  (2020-09-23T22:33:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.