Research Papers

High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circuits to structured semantic directions that align with human-interpretable concepts. While the Linear Representation Hypothesis (LRH) suggests that such directions emerge in representations, it remains unclear how these representations originate and why they become increasingly stable across layers. To solve this issue, we introduce the Input-Space Linearity Hypothesis, positing that concept-aligned directions originate in the input space and are steadily maintained with increasing depth. We then propose the Spectral Principal Path (SPP) framework, which formalizes how deep networks progressively distill linear representations along the spectral principal directions. We provide rigorous stability guarantees for the SPP based on the Wedin $\sinΘ$ perturbation theorem, identifying testable conditions, including spectral gap and context incoherence, that jointly ensure layer-wise directional preservation. By bridging theoretical analysis with empirical evidence, this work identifies a spectral view of how linear representations arise in LLMs, and suggests potential implications for concept-level controllable, robust, and coherent approaches to fairness and transparency in modern AI systems.

As artificial intelligence (AI) systems become deeply embedded in everyday life, calls to align AI development with ethical and societal values have intensified. Interdisciplinary collaboration is often championed as a key pathway for fostering such engagement. Yet it remains unclear whether interdisciplinary research teams are actually leading this shift in practice. This study analyzes over 100,000 AI-related papers published on ArXiv between 2014 and 2024 to examine how ethical values and societal concerns are integrated into technical AI research. We develop a classifier to identify societal content and measure the extent to which research papers express these considerations. We find a striking shift: while interdisciplinary teams remain more likely to produce societally-oriented research, computer science-only teams now account for a growing share of the field's overall societal output. These teams are increasingly integrating societal concerns into their papers and tackling a wide range of domains - from fairness and safety to healthcare and misinformation. These findings challenge common assumptions about the drivers of societal AI and raise important questions. First, what are the implications for emerging understandings of AI safety and governance if most societally-oriented research is being undertaken by exclusively technical teams? Second, for scholars in the social sciences and humanities: in a technical field increasingly responsive to societal demands, what distinctive perspectives can we still offer to help shape the future of AI?

AI models have become active decision makers, often acting without human supervision. The rapid advancement of AI technology has already caused harmful incidents that have hurt individuals and societies and AI unfairness in heavily criticized. It is urgent to disrupt AI pipelines which largely neglect human principles and focus on computational biases exploration at the data (pre), model(in), and deployment (post) processing stages. We claim that by exploiting the advances of agents technology, we will introduce cautious, prompt, and ongoing fairness watch schemes, under realistic, systematic, and human-centric fairness expectations. We envision agents as fairness guardians, since agents learn from their environment, adapt to new information, and solve complex problems by interacting with external tools and other systems. To set the proper fairness guardrails in the overall AI pipeline, we introduce a fairness-by-design approach which embeds multi-role agents in an end-to-end (human to AI) synergetic scheme. Our position is that we may design adaptive and realistic AI fairness frameworks, and we introduce a generalized algorithm which can be customized to the requirements and goals of each AI decision making scenario. Our proposed, so called FAIRTOPIA framework, is structured over a three-layered architecture, which encapsulates the AI pipeline inside an agentic guardian and a knowledge-based, self-refining layered scheme. Based on our proposition, we enact fairness watch in all of the AI pipeline stages, under robust multi-agent workflows, which will inspire new fairness research hypothesis, heuristics, and methods grounded in human-centric, systematic, interdisciplinary, socio-technical principles.

Large Language Models (LLMs) can generate plausible free text self-explanations to justify their answers. However, these natural language explanations may not accurately reflect the model's actual reasoning process, pinpointing a lack of faithfulness. Existing faithfulness evaluation methods rely primarily on behavioral tests or computational block analysis without examining the semantic content of internal neural representations. This paper proposes NeuroFaith, a flexible framework that measures the faithfulness of LLM free text self-explanation by identifying key concepts within explanations and mechanistically testing whether these concepts actually influence the model's predictions. We show the versatility of NeuroFaith across 2-hop reasoning and classification tasks. Additionally, we develop a linear faithfulness probe based on NeuroFaith to detect unfaithful self-explanations from representation space and improve faithfulness through steering. NeuroFaith provides a principled approach to evaluating and enhancing the faithfulness of LLM free text self-explanations, addressing critical needs for trustworthy AI systems.

COVID-19 is a rapidly spreading and highly infectious virus which has triggered a global pandemic, profoundly affecting millions across the world. The pandemic has introduced unprecedented challenges in public health, economic stability, and societal structures, necessitating the implementation of extensive and multifaceted health interventions globally. It had a tremendous impact on Bangladesh by April 2024, with around 29,495 fatalities and more than 2 million confirmed cases. This study focuses on improving COVID-19 detection in CXR images by utilizing a dataset of 4,350 images from Bangladesh categorized into four classes: Normal, Lung-Opacity, COVID-19 and Viral-Pneumonia. ML, DL and TL models are employed with the VGG19 model achieving an impressive 98% accuracy. LIME is used to explain model predictions, highlighting the regions and features influencing classification decisions. SMOTE is applied to address class imbalances. By providing insight into both correct and incorrect classifications, the study emphasizes the importance of XAI in enhancing the transparency and reliability of models, ultimately improving the effectiveness of detection from CXR images.

Do Protein Transformers Have Biological Intelligence?

Fudong Lin, Wanrou Du, Jinchan Liu +5

Deep neural networks, particularly Transformers, have been widely adopted for predicting the functional properties of proteins. In this work, we focus on exploring whether Protein Transformers can capture biological intelligence among protein sequences. To achieve our goal, we first introduce a protein function dataset, namely Protein-FN, providing over 9000 protein data with meaningful labels. Second, we devise a new Transformer architecture, namely Sequence Protein Transformers (SPT), for computationally efficient protein function predictions. Third, we develop a novel Explainable Artificial Intelligence (XAI) technique called Sequence Score, which can efficiently interpret the decision-making processes of protein models, thereby overcoming the difficulty of deciphering biological intelligence bided in Protein Transformers. Remarkably, even our smallest SPT-Tiny model, which contains only 5.4M parameters, demonstrates impressive predictive accuracy, achieving 94.3% on the Antibiotic Resistance (AR) dataset and 99.6% on the Protein-FN dataset, all accomplished by training from scratch. Besides, our Sequence Score technique helps reveal that our SPT models can discover several meaningful patterns underlying the sequence structures of protein data, with these patterns aligning closely with the domain knowledge in the biology community. We have officially released our Protein-FN dataset on Hugging Face Datasets https://huggingface.co/datasets/Protein-FN/Protein-FN. Our code is available at https://github.com/fudong03/BioIntelligence.

In efforts toward achieving responsible artificial intelligence (AI), fostering a culture of workplace transparency, diversity, and inclusion can breed innovation, trust, and employee contentment. In AI and Machine Learning (ML), such environments correlate with higher standards of responsible development. Without transparency, disparities, microaggressions and misconduct will remain unaddressed, undermining the very structural inequities responsible AI aims to mitigate. While prior work investigates workplace transparency and disparities in broad domains (e.g. science and technology, law) for specific demographic subgroups, it lacks in-depth and intersectional conclusions and a focus on the AI/ML community. To address this, we conducted a pilot survey of 1260 AI/ML professionals both in industry and academia across different axes, probing aspects such as belonging, performance, workplace Diversity, Equity and Inclusion (DEI) initiatives, accessibility, performance and compensation, microaggressions, misconduct, growth, and well-being. Results indicate enduring disparities in workplace experiences for underrepresented and/or marginalized subgroups. In particular, we highlight that accessibility remains an important challenge for a positive work environment and that disabled employees have a worse workplace experience than their non-disabled colleagues. We further surface disparities for intersectional groups and discuss how the implementation of DEI initiatives may differ from their perceived impact on the workplace. This study is a first step towards increasing transparency and informing AI/ML practitioners and organizations with empirical results. We aim to foster equitable decision-making in the design and evaluation of organizational policies and provide data that may empower professionals to make more informed choices of prospective workplaces.

A prevailing approach to explain time series models is to generate attribution in time domain. A recent development in time series XAI is the concept of explanation spaces, where any model trained in the time domain can be interpreted with any existing XAI method in alternative domains, such as frequency. The prevailing approach is to present XAI attributions either in the time domain or in the domain where the attribution is most sparse. In this paper, we demonstrate that in certain cases, XAI methods can generate attributions that highlight fundamentally different features in the time and frequency domains that are not direct counterparts of one another. This suggests that both domains' attributions should be presented to achieve a more comprehensive interpretation. Thus it shows the necessity of multi-domain explanation. To quantify when such cases arise, we introduce the uncertainty principle (UP), originally developed in quantum mechanics and later studied in harmonic analysis and signal processing, to the XAI literature. This principle establishes a lower bound on how much a signal can be simultaneously localized in both the time and frequency domains. By leveraging this concept, we assess whether attributions in the time and frequency domains violate this bound, indicating that they emphasize distinct features. In other words, UP provides a sufficient condition that the time and frequency domain explanations do not match and, hence, should be both presented to the end user. We validate the effectiveness of this approach across various deep learning models, XAI methods, and a wide range of classification and forecasting datasets. The frequent occurrence of UP violations across various datasets and XAI methods highlights the limitations of existing approaches that focus solely on time-domain explanations. This underscores the need for multi-domain explanations as a new paradigm.

Representational Difference Explanations

Neehar Kondapaneni, Oisin Mac Aodha, Pietro Perona

We propose a method for discovering and visualizing the differences between two learned representations, enabling more direct and interpretable model comparisons. We validate our method, which we call Representational Differences Explanations (RDX), by using it to compare models with known conceptual differences and demonstrate that it recovers meaningful distinctions where existing explainable AI (XAI) techniques fail. Applied to state-of-the-art models on challenging subsets of the ImageNet and iNaturalist datasets, RDX reveals both insightful representational differences and subtle patterns in the data. Although comparison is a cornerstone of scientific analysis, current tools in machine learning, namely post hoc XAI methods, struggle to support model comparison effectively. Our work addresses this gap by introducing an effective and explainable tool for contrasting model representations.

This study introduces a novel conceptual framework distinguishing problem-seeking from problem-solving to clarify the unique features of human intelligence in contrast to AI. Problem-seeking refers to the embodied, emotionally grounded process by which humans identify and set goals, while problem-solving denotes the execution of strategies aimed at achieving such predefined objectives. The framework emphasizes that while AI excels at efficiency and optimization, it lacks the orientation derived from experiential grounding and the embodiment flexibility intrinsic to human cognition. To empirically explore this distinction, the research analyzes metadata from 157 YouTube videos discussing AI. Conducting a thematic analysis combining qualitative insights with keyword-based quantitative metrics, this mixed-methods approach uncovers recurring themes in public discourse, including privacy, job displacement, misinformation, optimism, and ethical concerns. The results reveal a dual sentiment: public fascination with AI's capabilities coexists with anxiety and skepticism about its societal implications. The discussion critiques the orthogonality thesis, which posits that intelligence is separable from goal content, and instead argues that human intelligence integrates goal-setting and goal-pursuit. It underscores the centrality of embodied cognition in human reasoning and highlights how AI's limitations come from its current reliance on computational processing. The study advocates for enhancing emotional and digital literacy to foster responsible AI engagement. It calls for reframing public discourse to recognize AI as a tool that augments -- rather than replaces -- human intelligence. By positioning problem seeking at the core of cognition and as a critical dimension of intelligence, this research offers new perspectives on ethically aligned and human-centered AI development.

Deep neural networks form the backbone of artificial intelligence research, with potential to transform the human experience in areas ranging from autonomous driving to personal assistants, healthcare to education. However, their integration into the daily routines of real-world classrooms remains limited. It is not yet common for a teacher to assign students individualized homework targeting their specific weaknesses, provide students with instant feedback, or simulate student responses to a new exam question. While these models excel in predictive performance, this lack of adoption can be attributed to a significant weakness: the lack of explainability of model decisions, leading to a lack of trust from students, parents, and teachers. This thesis aims to bring human needs to the forefront of eXplainable AI (XAI) research, grounded in the concrete use case of personalized learning and teaching. We frame the contributions along two verticals: technical advances in XAI and their aligned human studies. We investigate explainability in AI for education, revealing systematic disagreements between post-hoc explainers and identifying a need for inherently interpretable model architectures. We propose four novel technical contributions in interpretability with a multimodal modular architecture (MultiModN), an interpretable mixture-of-experts model (InterpretCC), adversarial training for explainer stability, and a theory-driven LLM-XAI framework to present explanations to students (iLLuMinaTE), which we evaluate in diverse settings with professors, teachers, learning scientists, and university students. By combining empirical evaluations of existing explainers with novel architectural designs and human studies, our work lays a foundation for human-centric AI systems that balance state-of-the-art performance with built-in transparency and trust.

Limited DXA access hinders osteoporosis screening. This proof-of-concept study proposes using widely available knee X-rays for opportunistic Bone Mineral Density (BMD) estimation via deep learning, emphasizing robust uncertainty quantification essential for clinical use. An EfficientNet model was trained on the OAI dataset to predict BMD from bilateral knee radiographs. Two Test-Time Augmentation (TTA) methods were compared: traditional averaging and a multi-sample approach. Crucially, Split Conformal Prediction was implemented to provide statistically rigorous, patient-specific prediction intervals with guaranteed coverage. Results showed a Pearson correlation of 0.68 (traditional TTA). While traditional TTA yielded better point predictions, the multi-sample approach produced slightly tighter confidence intervals (90%, 95%, 99%) while maintaining coverage. The framework appropriately expressed higher uncertainty for challenging cases. Although anatomical mismatch between knee X-rays and standard DXA limits immediate clinical use, this method establishes a foundation for trustworthy AI-assisted BMD screening using routine radiographs, potentially improving early osteoporosis detection.