Data Bias
University of Pennsylvann
Abstract
Mainstream news organizations shape public perception not only directly through the articles they publish but also through the choices they make about which topics to cover (or ignore) and how to frame the issues they do decide to cover. However, measuring these subtle forms of media bias at scale remains a challenge. Here, we introduce a large, ongoing (from January 1, 2024 to present), near real-time dataset and computational framework developed to enable systematic study of selection and framing bias in news coverage. Our pipeline integrates large language models (LLMs) with scalable, near-real-time news scraping to extract structured annotations -- including political lean, tone, topics, article type, and major events -- across hundreds of articles per day. We quantify these dimensions of coverage at multiple levels -- the sentence level, the article level, and the publisher level -- expanding the ways in which researchers can analyze media bias in the modern news landscape. In addition to a curated dataset, we also release an interactive web platform for convenient exploration of these data. Together, these contributions establish a reusable methodology for studying media bias at scale, providing empirical resources for future research. Leveraging the breadth of the corpus over time and across publishers, we also present some examples (focused on the 150,000+ articles examined in 2024) that illustrate how this novel data set can reveal insightful patterns in news coverage and bias, supporting academic research and real-world efforts to improve media accountability.
Mainstream news organizations shape public perception not only directly through the articles they publish but also through the choices they make about which topics to cover (or ignore) and how to frame the issues they do decide to cover. However, measuring these subtle forms of media bias at scale remains a challenge. Here, we introduce a large, ongoing (from January 1, 2024 to present), near real-time dataset and computational framework developed to enable systematic study of selection and framing bias in news coverage. Our pipeline integrates large language models (LLMs) with scalable, near-real-time news scraping to extract structured annotations -- including political lean, tone, topics, article type, and major events -- across hundreds of articles per day. We quantify these dimensions of coverage at multiple levels -- the sentence level, the article level, and the publisher level -- expanding the ways in which researchers can analyze media bias in the modern news landscape. In addition to a curated dataset, we also release an interactive web platform for convenient exploration of these data. Together, these contributions establish a reusable methodology for studying media bias at scale, providing empirical resources for future research. Leveraging the breadth of the corpus over time and across publishers, we also present some examples (focused on the 150,000+ articles examined in 2024) that illustrate how this novel data set can reveal insightful patterns in news coverage and bias, supporting academic research and real-world efforts to improve media accountability.
Abstract
Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain attributes and target labels in training data. These biases are often more prevalent and easier to learn, causing models to rely on superficial patterns rather than task-relevant features necessary for generalization. Existing methods typically rely on strong assumptions, such as prior knowledge of these biases or access to bias-conflicting samples, i.e., samples that contradict spurious correlations and counterbalance bias-aligned samples, samples that conform to these spurious correlations. However, such assumptions are often impractical in real-world settings. We propose BLADE ({B}ias-{L}inked {A}daptive {DE}biasing), a generative debiasing framework that requires no prior knowledge of bias or bias-conflicting samples. BLADE first trains a generative model to translate images across bias domains while preserving task-relevant features. Then, it adaptively refines each image with its synthetic counterpart based on the image's susceptibility to bias. To encourage robust representations, BLADE aligns an image with its bias-translated synthetic counterpart that shares task-relevant features but differs in bias, while misaligning it with samples sharing the same bias. We evaluate BLADE on multiple benchmark datasets and show that it significantly outperforms state-of-the-art methods. Notably, it exceeds the closest baseline by an absolute margin of around 18% on the corrupted CIFAR-10 dataset under the worst group setting, establishing a new benchmark in bias mitigation and demonstrating its potential for developing more robust deep learning models without explicit supervision.
Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain attributes and target labels in training data. These biases are often more prevalent and easier to learn, causing models to rely on superficial patterns rather than task-relevant features necessary for generalization. Existing methods typically rely on strong assumptions, such as prior knowledge of these biases or access to bias-conflicting samples, i.e., samples that contradict spurious correlations and counterbalance bias-aligned samples, samples that conform to these spurious correlations. However, such assumptions are often impractical in real-world settings. We propose BLADE ({B}ias-{L}inked {A}daptive {DE}biasing), a generative debiasing framework that requires no prior knowledge of bias or bias-conflicting samples. BLADE first trains a generative model to translate images across bias domains while preserving task-relevant features. Then, it adaptively refines each image with its synthetic counterpart based on the image's susceptibility to bias. To encourage robust representations, BLADE aligns an image with its bias-translated synthetic counterpart that shares task-relevant features but differs in bias, while misaligning it with samples sharing the same bias. We evaluate BLADE on multiple benchmark datasets and show that it significantly outperforms state-of-the-art methods. Notably, it exceeds the closest baseline by an absolute margin of around 18% on the corrupted CIFAR-10 dataset under the worst group setting, establishing a new benchmark in bias mitigation and demonstrating its potential for developing more robust deep learning models without explicit supervision.
Data Transparency
University of Porto
Abstract
Due to the susceptibility of Artificial Intelligence (AI) to data perturbations and adversarial examples, it is crucial to perform a thorough robustness evaluation before any Machine Learning (ML) model is deployed. However, examining a model's decision boundaries and identifying potential vulnerabilities typically requires access to the training and testing datasets, which may pose risks to data privacy and confidentiality. To improve transparency in organizations that handle confidential data or manage critical infrastructure, it is essential to allow external verification and validation of AI without the disclosure of private datasets. This paper presents Systematic Pattern Analysis (SPATA), a deterministic method that converts any tabular dataset to a domain-independent representation of its statistical patterns, to provide more detailed and transparent data cards. SPATA computes the projection of each data instance into a discrete space where they can be analyzed and compared, without risking data leakage. These projected datasets can be reliably used for the evaluation of how different features affect ML model robustness and for the generation of interpretable explanations of their behavior, contributing to more trustworthy AI.
Due to the susceptibility of Artificial Intelligence (AI) to data perturbations and adversarial examples, it is crucial to perform a thorough robustness evaluation before any Machine Learning (ML) model is deployed. However, examining a model's decision boundaries and identifying potential vulnerabilities typically requires access to the training and testing datasets, which may pose risks to data privacy and confidentiality. To improve transparency in organizations that handle confidential data or manage critical infrastructure, it is essential to allow external verification and validation of AI without the disclosure of private datasets. This paper presents Systematic Pattern Analysis (SPATA), a deterministic method that converts any tabular dataset to a domain-independent representation of its statistical patterns, to provide more detailed and transparent data cards. SPATA computes the projection of each data instance into a discrete space where they can be analyzed and compared, without risking data leakage. These projected datasets can be reliably used for the evaluation of how different features affect ML model robustness and for the generation of interpretable explanations of their behavior, contributing to more trustworthy AI.
Abstract
Ensuring the trustworthiness of data from distributed and resource-constrained environments, such as Wireless Sensor Networks or IoT devices, is critical. Existing Reversible Data Hiding (RDH) methods for scalar data suffer from low embedding capacity and poor intrinsic mixing between host data and watermark. This paper introduces Hiding in the Imaginary Domain with Data Encryption (H[i]dden), a novel framework based on complex number arithmetic for simultaneous information embedding and encryption. The H[i]dden framework offers perfect reversibility, in-principle unlimited watermark size, and intrinsic data-watermark mixing. The paper further introduces two protocols: H[i]dden-EG, for joint reversible data hiding and encryption, and H[i]dden-AggP, for privacy-preserving aggregation of watermarked data, based on partially homomorphic encryption. These protocols provide efficient and resilient solutions for data integrity, provenance and confidentiality, serving as a foundation for new schemes based on the algebraic properties of the complex domain.
Ensuring the trustworthiness of data from distributed and resource-constrained environments, such as Wireless Sensor Networks or IoT devices, is critical. Existing Reversible Data Hiding (RDH) methods for scalar data suffer from low embedding capacity and poor intrinsic mixing between host data and watermark. This paper introduces Hiding in the Imaginary Domain with Data Encryption (H[i]dden), a novel framework based on complex number arithmetic for simultaneous information embedding and encryption. The H[i]dden framework offers perfect reversibility, in-principle unlimited watermark size, and intrinsic data-watermark mixing. The paper further introduces two protocols: H[i]dden-EG, for joint reversible data hiding and encryption, and H[i]dden-AggP, for privacy-preserving aggregation of watermarked data, based on partially homomorphic encryption. These protocols provide efficient and resilient solutions for data integrity, provenance and confidentiality, serving as a foundation for new schemes based on the algebraic properties of the complex domain.
Data Fairness
Columbia University
Abstract
The wide adoption of AI decision-making systems in critical domains such as criminal justice, loan approval, and hiring processes has heightened concerns about algorithmic fairness. As we often only have access to the output of algorithms without insights into their internal mechanisms, it was natural to examine how decisions would alter when auxiliary sensitive attributes (such as race) change. This led the research community to come up with counterfactual fairness measures, but how to evaluate the measure from available data remains a challenging task. In many practical applications, the target counterfactual measure is not identifiable, i.e., it cannot be uniquely determined from the combination of quantitative data and qualitative knowledge. This paper addresses this challenge using partial identification, which derives informative bounds over counterfactual fairness measures from observational data. We introduce a Bayesian approach to bound unknown counterfactual fairness measures with high confidence. We demonstrate our algorithm on the COMPAS dataset, examining fairness in recidivism risk scores with respect to race, age, and sex. Our results reveal a positive (spurious) effect on the COMPAS score when changing race to African-American (from all others) and a negative (direct causal) effect when transitioning from young to old age.
The wide adoption of AI decision-making systems in critical domains such as criminal justice, loan approval, and hiring processes has heightened concerns about algorithmic fairness. As we often only have access to the output of algorithms without insights into their internal mechanisms, it was natural to examine how decisions would alter when auxiliary sensitive attributes (such as race) change. This led the research community to come up with counterfactual fairness measures, but how to evaluate the measure from available data remains a challenging task. In many practical applications, the target counterfactual measure is not identifiable, i.e., it cannot be uniquely determined from the combination of quantitative data and qualitative knowledge. This paper addresses this challenge using partial identification, which derives informative bounds over counterfactual fairness measures from observational data. We introduce a Bayesian approach to bound unknown counterfactual fairness measures with high confidence. We demonstrate our algorithm on the COMPAS dataset, examining fairness in recidivism risk scores with respect to race, age, and sex. Our results reveal a positive (spurious) effect on the COMPAS score when changing race to African-American (from all others) and a negative (direct causal) effect when transitioning from young to old age.
University of Central FL
Abstract
As AI systems become more embedded in everyday life, the development of fair and unbiased models becomes more critical. Considering the social impact of AI systems is not merely a technical challenge but a moral imperative. As evidenced in numerous research studies, learning fair and robust representations has proven to be a powerful approach to effectively debiasing algorithms and improving fairness while maintaining essential information for prediction tasks. Representation learning frameworks, particularly those that utilize self-supervised and contrastive learning, have demonstrated superior robustness and generalizability across various domains. Despite the growing interest in applying these approaches to tabular data, the issue of fairness in these learned representations remains underexplored. In this study, we introduce a contrastive learning framework specifically designed to address bias and learn fair representations in tabular datasets. By strategically selecting positive pair samples and employing supervised and self-supervised contrastive learning, we significantly reduce bias compared to existing state-of-the-art contrastive learning models for tabular data. Our results demonstrate the efficacy of our approach in mitigating bias with minimum trade-off in accuracy and leveraging the learned fair representations in various downstream tasks.
As AI systems become more embedded in everyday life, the development of fair and unbiased models becomes more critical. Considering the social impact of AI systems is not merely a technical challenge but a moral imperative. As evidenced in numerous research studies, learning fair and robust representations has proven to be a powerful approach to effectively debiasing algorithms and improving fairness while maintaining essential information for prediction tasks. Representation learning frameworks, particularly those that utilize self-supervised and contrastive learning, have demonstrated superior robustness and generalizability across various domains. Despite the growing interest in applying these approaches to tabular data, the issue of fairness in these learned representations remains underexplored. In this study, we introduce a contrastive learning framework specifically designed to address bias and learn fair representations in tabular datasets. By strategically selecting positive pair samples and employing supervised and self-supervised contrastive learning, we significantly reduce bias compared to existing state-of-the-art contrastive learning models for tabular data. Our results demonstrate the efficacy of our approach in mitigating bias with minimum trade-off in accuracy and leveraging the learned fair representations in various downstream tasks.
AI Fairness
University of Washington
Abstract
The European Union's AI Act represents a crucial step towards regulating ethical and responsible AI systems. However, we find an absence of quantifiable fairness metrics and the ambiguity in terminology, particularly the interchangeable use of the keywords transparency, explainability, and interpretability in the new EU AI Act and no reference of transparency of ethical compliance. We argue that this ambiguity creates substantial liability risk that would deter investment. Fairness transparency is strategically important. We recommend a more tailored regulatory framework to enhance the new EU AI regulation. Further-more, we propose a public system framework to assess the fairness and transparency of AI systems. Drawing from past work, we advocate for the standardization of industry best practices as a necessary addition to broad regulations to achieve the level of details required in industry, while preventing stifling innovation and investment in the AI sector. The proposals are exemplified with the case of ASR and speech synthesizers.
The European Union's AI Act represents a crucial step towards regulating ethical and responsible AI systems. However, we find an absence of quantifiable fairness metrics and the ambiguity in terminology, particularly the interchangeable use of the keywords transparency, explainability, and interpretability in the new EU AI Act and no reference of transparency of ethical compliance. We argue that this ambiguity creates substantial liability risk that would deter investment. Fairness transparency is strategically important. We recommend a more tailored regulatory framework to enhance the new EU AI regulation. Further-more, we propose a public system framework to assess the fairness and transparency of AI systems. Drawing from past work, we advocate for the standardization of industry best practices as a necessary addition to broad regulations to achieve the level of details required in industry, while preventing stifling innovation and investment in the AI sector. The proposals are exemplified with the case of ASR and speech synthesizers.
The Australian National
Abstract
Artificial intelligence (AI) systems in high-stakes domains raise concerns about proxy discrimination, unfairness, and explainability. Existing audits often fail to reveal why unfairness arises, particularly when rooted in structural bias. We propose a novel framework using formal abductive explanations to explain proxy discrimination in individual AI decisions. Leveraging background knowledge, our method identifies which features act as unjustified proxies for protected attributes, revealing hidden structural biases. Central to our approach is the concept of aptitude, a task-relevant property independent of group membership, with a mapping function aligning individuals of equivalent aptitude across groups to assess fairness substantively. As a proof of concept, we showcase the framework with examples taken from the German credit dataset, demonstrating its applicability in real-world cases.
Artificial intelligence (AI) systems in high-stakes domains raise concerns about proxy discrimination, unfairness, and explainability. Existing audits often fail to reveal why unfairness arises, particularly when rooted in structural bias. We propose a novel framework using formal abductive explanations to explain proxy discrimination in individual AI decisions. Leveraging background knowledge, our method identifies which features act as unjustified proxies for protected attributes, revealing hidden structural biases. Central to our approach is the concept of aptitude, a task-relevant property independent of group membership, with a mapping function aligning individuals of equivalent aptitude across groups to assess fairness substantively. As a proof of concept, we showcase the framework with examples taken from the German credit dataset, demonstrating its applicability in real-world cases.
Data Ethics
University College Cork
Abstract
This chapter presents a comprehensive taxonomy for assessing data quality in the context of data monetisation, developed through a systematic literature review. Organising over one hundred metrics and Key Performance Indicators (KPIs) into four subclusters (Fundamental, Contextual, Resolution, and Specialised) within the Balanced Scorecard (BSC) framework, the taxonomy integrates both universal and domain-specific quality dimensions. By positioning data quality as a strategic connector across the BSC's Financial, Customer, Internal Processes, and Learning & Growth perspectives, it demonstrates how quality metrics underpin valuation accuracy, customer trust, operational efficiency, and innovation capacity. The framework's interconnected "metrics layer" ensures that improvements in one dimension cascade into others, maximising strategic impact. This holistic approach bridges the gap between granular technical assessment and high-level decision-making, offering practitioners, data stewards, and strategists a scalable, evidence-based reference for aligning data quality management with sustainable value creation.
This chapter presents a comprehensive taxonomy for assessing data quality in the context of data monetisation, developed through a systematic literature review. Organising over one hundred metrics and Key Performance Indicators (KPIs) into four subclusters (Fundamental, Contextual, Resolution, and Specialised) within the Balanced Scorecard (BSC) framework, the taxonomy integrates both universal and domain-specific quality dimensions. By positioning data quality as a strategic connector across the BSC's Financial, Customer, Internal Processes, and Learning & Growth perspectives, it demonstrates how quality metrics underpin valuation accuracy, customer trust, operational efficiency, and innovation capacity. The framework's interconnected "metrics layer" ensures that improvements in one dimension cascade into others, maximising strategic impact. This holistic approach bridges the gap between granular technical assessment and high-level decision-making, offering practitioners, data stewards, and strategists a scalable, evidence-based reference for aligning data quality management with sustainable value creation.
University of LAquila
Abstract
Large Language Models (LLMs) are increasingly integrated into software engineering (SE) tools for tasks that extend beyond code synthesis, including judgment under uncertainty and reasoning in ethically significant contexts. We present a fully automated framework for assessing ethical reasoning capabilities across 16 LLMs in a zero-shot setting, using 30 real-world ethically charged scenarios. Each model is prompted to identify the most applicable ethical theory to an action, assess its moral acceptability, and explain the reasoning behind their choice. Responses are compared against expert ethicists' choices using inter-model agreement metrics. Our results show that LLMs achieve an average Theory Consistency Rate (TCR) of 73.3% and Binary Agreement Rate (BAR) on moral acceptability of 86.7%, with interpretable divergences concentrated in ethically ambiguous cases. A qualitative analysis of free-text explanations reveals strong conceptual convergence across models despite surface-level lexical diversity. These findings support the potential viability of LLMs as ethical inference engines within SE pipelines, enabling scalable, auditable, and adaptive integration of user-aligned ethical reasoning. Our focus is the Ethical Interpreter component of a broader profiling pipeline: we evaluate whether current LLMs exhibit sufficient interpretive stability and theory-consistent reasoning to support automated profiling.
Large Language Models (LLMs) are increasingly integrated into software engineering (SE) tools for tasks that extend beyond code synthesis, including judgment under uncertainty and reasoning in ethically significant contexts. We present a fully automated framework for assessing ethical reasoning capabilities across 16 LLMs in a zero-shot setting, using 30 real-world ethically charged scenarios. Each model is prompted to identify the most applicable ethical theory to an action, assess its moral acceptability, and explain the reasoning behind their choice. Responses are compared against expert ethicists' choices using inter-model agreement metrics. Our results show that LLMs achieve an average Theory Consistency Rate (TCR) of 73.3% and Binary Agreement Rate (BAR) on moral acceptability of 86.7%, with interpretable divergences concentrated in ethically ambiguous cases. A qualitative analysis of free-text explanations reveals strong conceptual convergence across models despite surface-level lexical diversity. These findings support the potential viability of LLMs as ethical inference engines within SE pipelines, enabling scalable, auditable, and adaptive integration of user-aligned ethical reasoning. Our focus is the Ethical Interpreter component of a broader profiling pipeline: we evaluate whether current LLMs exhibit sufficient interpretive stability and theory-consistent reasoning to support automated profiling.
Data Representation
European Southern Observa
Abstract
ADARI (Astronomical DAta Reporting Infrastructure) is a system designed for creating graphical reports of astronomical data so that the quality of these products can be assessed. It has been designed from the ground up to be backend-agnostic, meaning the same ADARI code can be sent to a web plotting API, or a code-based plotting API, with no alteration. Quick data inspection is an important feature in data reduction systems. The use cases range from quality control at the telescope, advance quality checks prior to delivering data to the scientists as well as data inspection for users running the pipelines at their home institutes. The goal of ADARI is to deliver the same experience and code for data visualization for all the environments, either running automatically in the Paranal Observatory environment or at the PI premises. ADARI contains a library that can be used to develop the creation of reports as well as a command line tool (genreport) to execute such reports. Most of the time the reports are generated as part of the execution of a data reduction workflow implemented with EDPS, the new ESO system for automatically organising data from ESO instruments and for running the reduction pipelines on them.
ADARI (Astronomical DAta Reporting Infrastructure) is a system designed for creating graphical reports of astronomical data so that the quality of these products can be assessed. It has been designed from the ground up to be backend-agnostic, meaning the same ADARI code can be sent to a web plotting API, or a code-based plotting API, with no alteration. Quick data inspection is an important feature in data reduction systems. The use cases range from quality control at the telescope, advance quality checks prior to delivering data to the scientists as well as data inspection for users running the pipelines at their home institutes. The goal of ADARI is to deliver the same experience and code for data visualization for all the environments, either running automatically in the Paranal Observatory environment or at the PI premises. ADARI contains a library that can be used to develop the creation of reports as well as a command line tool (genreport) to execute such reports. Most of the time the reports are generated as part of the execution of a data reduction workflow implemented with EDPS, the new ESO system for automatically organising data from ESO instruments and for running the reduction pipelines on them.
Vanderbilt University, YU
Abstract
Protein function is driven by coherent substructures which vary in size and topology, yet current protein representation learning models (PRL) distort these signals by relying on rigid substructures such as k-hop and fixed radius neighbourhoods. We introduce BioBlobs, a plug-and-play, fully differentiable module that represents proteins by dynamically partitioning structures into flexibly-sized, non-overlapping substructures ("blobs"). The resulting blobs are quantized into a shared and interpretable codebook, yielding a discrete vocabulary of function-relevant protein substructures used to compute protein embeddings. We show that BioBlobs representations improve the performance of widely used protein encoders such as GVP-GNN across various PRL tasks. Our approach highlights the value of architectures that directly capture function-relevant protein substructures, enabling both improved predictive performance and mechanistic insight into protein function.
Protein function is driven by coherent substructures which vary in size and topology, yet current protein representation learning models (PRL) distort these signals by relying on rigid substructures such as k-hop and fixed radius neighbourhoods. We introduce BioBlobs, a plug-and-play, fully differentiable module that represents proteins by dynamically partitioning structures into flexibly-sized, non-overlapping substructures ("blobs"). The resulting blobs are quantized into a shared and interpretable codebook, yielding a discrete vocabulary of function-relevant protein substructures used to compute protein embeddings. We show that BioBlobs representations improve the performance of widely used protein encoders such as GVP-GNN across various PRL tasks. Our approach highlights the value of architectures that directly capture function-relevant protein substructures, enabling both improved predictive performance and mechanistic insight into protein function.
AI Bias
Czech Technical Universty
Abstract
There is a strong recent emphasis on trustworthy AI. In particular, international regulations, such as the AI Act, demand that AI practitioners measure data quality on the input and estimate bias on the output of high-risk AI systems. However, there are many challenges involved, including scalability (MMD) and computability (Wasserstein-1) issues of traditional methods for estimating distances on measure spaces. Here, we present humancompatible.detect, a toolkit for bias detection that addresses these challenges. It incorporates two newly developed methods to detect and evaluate bias: maximum subgroup discrepancy (MSD) and subsampled $\ell_\infty$ distances. It has an easy-to-use API documented with multiple examples. humancompatible.detect is licensed under the Apache License, Version 2.0.
There is a strong recent emphasis on trustworthy AI. In particular, international regulations, such as the AI Act, demand that AI practitioners measure data quality on the input and estimate bias on the output of high-risk AI systems. However, there are many challenges involved, including scalability (MMD) and computability (Wasserstein-1) issues of traditional methods for estimating distances on measure spaces. Here, we present humancompatible.detect, a toolkit for bias detection that addresses these challenges. It incorporates two newly developed methods to detect and evaluate bias: maximum subgroup discrepancy (MSD) and subsampled $\ell_\infty$ distances. It has an easy-to-use API documented with multiple examples. humancompatible.detect is licensed under the Apache License, Version 2.0.
AI Ethics
Northwestern University
Abstract
While research in AI methods for music generation and analysis has grown in scope and impact, AI researchers' engagement with the ethical consequences of this work has not kept pace. To encourage such engagement, many publication venues have introduced optional or required ethics statements for AI research papers. Though some authors use these ethics statements to critically engage with the broader implications of their research, we find that the majority of ethics statements in the AI music literature do not appear to be effectively utilized for this purpose. In this work, we conduct a review of ethics statements across ISMIR, NIME, and selected prominent works in AI music from the past five years. We then offer suggestions for both audio conferences and researchers for engaging with ethics statements in ways that foster meaningful reflection rather than formulaic compliance.
While research in AI methods for music generation and analysis has grown in scope and impact, AI researchers' engagement with the ethical consequences of this work has not kept pace. To encourage such engagement, many publication venues have introduced optional or required ethics statements for AI research papers. Though some authors use these ethics statements to critically engage with the broader implications of their research, we find that the majority of ethics statements in the AI music literature do not appear to be effectively utilized for this purpose. In this work, we conduct a review of ethics statements across ISMIR, NIME, and selected prominent works in AI music from the past five years. We then offer suggestions for both audio conferences and researchers for engaging with ethics statements in ways that foster meaningful reflection rather than formulaic compliance.
St Plten University of
Abstract
Artificial Intelligence has rapidly become a cornerstone technology, significantly influencing Europe's societal and economic landscapes. However, the proliferation of AI also raises critical ethical, legal, and regulatory challenges. The CERTAIN (Certification for Ethical and Regulatory Transparency in Artificial Intelligence) project addresses these issues by developing a comprehensive framework that integrates regulatory compliance, ethical standards, and transparency into AI systems. In this position paper, we outline the methodological steps for building the core components of this framework. Specifically, we present: (i) semantic Machine Learning Operations (MLOps) for structured AI lifecycle management, (ii) ontology-driven data lineage tracking to ensure traceability and accountability, and (iii) regulatory operations (RegOps) workflows to operationalize compliance requirements. By implementing and validating its solutions across diverse pilots, CERTAIN aims to advance regulatory compliance and to promote responsible AI innovation aligned with European standards.
Artificial Intelligence has rapidly become a cornerstone technology, significantly influencing Europe's societal and economic landscapes. However, the proliferation of AI also raises critical ethical, legal, and regulatory challenges. The CERTAIN (Certification for Ethical and Regulatory Transparency in Artificial Intelligence) project addresses these issues by developing a comprehensive framework that integrates regulatory compliance, ethical standards, and transparency into AI systems. In this position paper, we outline the methodological steps for building the core components of this framework. Specifically, we present: (i) semantic Machine Learning Operations (MLOps) for structured AI lifecycle management, (ii) ontology-driven data lineage tracking to ensure traceability and accountability, and (iii) regulatory operations (RegOps) workflows to operationalize compliance requirements. By implementing and validating its solutions across diverse pilots, CERTAIN aims to advance regulatory compliance and to promote responsible AI innovation aligned with European standards.
AI Transparency
Abstract
Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models possess self-recognition (Panickssery et al., 2024; Davidson et al., 2024), we introduce a systematic evaluation framework that can be easily applied and updated. Specifically, we measure how well 10 contemporary larger language models (LLMs) can identify their own generated text versus text from other models through two tasks: binary self-recognition and exact model prediction. Different from prior claims, our results reveal a consistent failure in self-recognition. Only 4 out of 10 models predict themselves as generators, and the performance is rarely above random chance. Additionally, models exhibit a strong bias toward predicting GPT and Claude families. We also provide the first evaluation of model awareness of their own and others' existence, as well as the reasoning behind their choices in self-recognition. We find that the model demonstrates some knowledge of its own existence and other models, but their reasoning reveals a hierarchical bias. They appear to assume that GPT, Claude, and occasionally Gemini are the top-tier models, often associating high-quality text with them. We conclude by discussing the implications of our findings on AI safety and future directions to develop appropriate AI self-awareness.
Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models possess self-recognition (Panickssery et al., 2024; Davidson et al., 2024), we introduce a systematic evaluation framework that can be easily applied and updated. Specifically, we measure how well 10 contemporary larger language models (LLMs) can identify their own generated text versus text from other models through two tasks: binary self-recognition and exact model prediction. Different from prior claims, our results reveal a consistent failure in self-recognition. Only 4 out of 10 models predict themselves as generators, and the performance is rarely above random chance. Additionally, models exhibit a strong bias toward predicting GPT and Claude families. We also provide the first evaluation of model awareness of their own and others' existence, as well as the reasoning behind their choices in self-recognition. We find that the model demonstrates some knowledge of its own existence and other models, but their reasoning reveals a hierarchical bias. They appear to assume that GPT, Claude, and occasionally Gemini are the top-tier models, often associating high-quality text with them. We conclude by discussing the implications of our findings on AI safety and future directions to develop appropriate AI self-awareness.
Kings College London
Abstract
Black-box explainability methods are popular tools for explaining the decisions of image classifiers. A major drawback of these tools is their reliance on mutants obtained by occluding parts of the input, leading to out-of-distribution images. This raises doubts about the quality of the explanations. Moreover, choosing an appropriate occlusion value often requires domain knowledge. In this paper we introduce a novel forward-pass paradigm Activation-Deactivation (AD), which removes the effects of occluded input features from the model's decision-making by switching off the parts of the model that correspond to the occlusions. We introduce ConvAD, a drop-in mechanism that can be easily added to any trained Convolutional Neural Network (CNN), and which implements the AD paradigm. This leads to more robust explanations without any additional training or fine-tuning. We prove that the ConvAD mechanism does not change the decision-making process of the network. We provide experimental evaluation across several datasets and model architectures. We compare the quality of AD-explanations with explanations achieved using a set of masking values, using the proxies of robustness, size, and confidence drop-off. We observe a consistent improvement in robustness of AD explanations (up to 62.5%) compared to explanations obtained with occlusions, demonstrating that ConvAD extracts more robust explanations without the need for domain knowledge.
Black-box explainability methods are popular tools for explaining the decisions of image classifiers. A major drawback of these tools is their reliance on mutants obtained by occluding parts of the input, leading to out-of-distribution images. This raises doubts about the quality of the explanations. Moreover, choosing an appropriate occlusion value often requires domain knowledge. In this paper we introduce a novel forward-pass paradigm Activation-Deactivation (AD), which removes the effects of occluded input features from the model's decision-making by switching off the parts of the model that correspond to the occlusions. We introduce ConvAD, a drop-in mechanism that can be easily added to any trained Convolutional Neural Network (CNN), and which implements the AD paradigm. This leads to more robust explanations without any additional training or fine-tuning. We prove that the ConvAD mechanism does not change the decision-making process of the network. We provide experimental evaluation across several datasets and model architectures. We compare the quality of AD-explanations with explanations achieved using a set of masking values, using the proxies of robustness, size, and confidence drop-off. We observe a consistent improvement in robustness of AD explanations (up to 62.5%) compared to explanations obtained with occlusions, demonstrating that ConvAD extracts more robust explanations without the need for domain knowledge.
Help us improve your experience!
This project is on its early stages your feedback can be pivotal on the future of the project.
Let us know what you think about this week's papers and suggestions!
Give Feedback