Research Papers

Beyond "I Can't Help With That": How Child Safety Experts Evaluate AI Chatbot Safety

Hannah Cha, Neha Shukla, Solon Barocas +3

Youth increasingly turn to AI chatbots for social and emotional support, raising concerns about how these systems respond, especially in high-stakes situations. However, existing child safety evaluations of AI lack grounding in real-world harms that youth experience, rely on unvalidated assumptions about what counts as an appropriate output (e.g., refusal), and typically focus on detecting adversarial prompts or surface-level harms in outputs only. Thus, these evaluations can fail to detect responses that pose harm to youth in practice. To better understand the limitations of current evaluation practices, we conducted interviews with 19 practitioners working directly with youth in vulnerable situations, including social workers, therapists, and psychologists, asking them to reflect on chatbots' responses to risky situations commonly faced by youth, as established in prior empirical work. Practitioners identified chatbot behaviors likely to cause harm as well as those that could meaningfully support youth in difficult moments, discussed the role that chatbots should (and should not) play in these interactions, and offered concrete recommendations for improving chatbot responses. Based on these findings, we provide recommendations for AI child safety evaluation and infrastructure, and highlight the need for incorporating practitioners' perspectives into safety work.

Generative AI output can contain errors, such as hallucinations, non-responsive results, or otherwise inaccurate or potentially harmful content. To explore the public's emerging understanding, attitudes, and behavior regarding such mistakes, we ran an online survey in the United States with 1,503 respondents, with a representative sample of the population. We report high public awareness of generative AI mistakes. Further, many respondents report checking generative AI output, for example, by comparing results with other online resources. We conclude with guidance for explanations and in-product disclosures about generative AI mistakes.

The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deepfake video benchmarks provide limited coverage of recent synthesis methods and generally lack reliable fine-grained textual annotations. Meanwhile, conventional detectors and multimodal large language models (MLLMs), whether operating as a single model or relying on a single analytical perspective, often fail to capture subtle forgery artifacts, limiting their generalization to emerging AI-generated methods. To address these limitations, we introduce FaceVid-Forensics-100K, a large-scale deepfake video dataset comprising 100,000 videos and spanning 33 synthesis methods across face swapping, face reenactment, and entire-face synthesis, including recent generators such as Seedance 2.0. The dataset provides fine-grained textual annotations of visual observations and verdict-consistent forensic explanations, automatically synthesized through a multi-model aggregation and conflict-resolution pipeline powered by advanced MLLMs. Building on this benchmark, we propose a multi-agent forensic reasoning framework that employs four specialized domain-expert agents to independently analyze forgery cues from four perspectives: texture, lighting, motion, and physics. A judge agent then reconciles their reports to produce a final prediction together with an explanation. Extensive evaluations on out-of-domain test sets show that, despite being composed entirely of small open-source MLLMs, our framework outperforms all methods including closed-source GPT and Gemini models and ranks first across all reported metrics on this benchmark. The project page is available at https://xavierjiezou.github.io/ARGUS/.

The rapid growth of artificial intelligence (AI) in music has expanded research from generation and information retrieval to education, health, and governance. Yet this growth does not necessarily imply balanced research attention. Where is research attention directed across diverse music tasks, and how can such imbalance be systematically measured? Existing studies examine AI music from separate technical, application-specific, or bibliometric perspectives, but lack a systematic framework for measuring field-level imbalance. To address this gap, we analyze 6,839 AI music publications from 2015 to April 2026 using a joint taxonomy of 12 application categories and 11 technical method families. We propose the Research Attention Profile, comprising four indicators of technical investment, method allocation, methodological diversity, and frontier-method adoption lag. Results show that technical support is concentrated in scalable, content-oriented tasks, while education, health, and governance remain under-supported. Generation adopts frontier methods after only 0.33 years on average, compared with 4.33 years for education and 5.00 years for health. These findings reveal uneven methodological development and support a more socially responsive AI music research agenda.

We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word Embedding Association Test (WEAT). WEAT is a bias measurement method widely used in both computational social science and AI fairness research. It relies on cosine similarity as a measure of semantic association, which assumes that the embedding space is approximately isotropic. However, prior work has reported that many widely used language models do not satisfy this assumption, raising concerns about the reliability of bias measurements. ZCA whitening transforms the covariance of the embedding space into the identity matrix while minimizing perturbation to the original vectors. This transformation restores the isotropy condition on which WEAT relies. We evaluate our approach on ten standard WEAT test suites and seven models spanning three architectural families, yielding 70 model-task combinations. The results show that ZCA whitening substantially reduces the anisotropy of the embedding spaces across all models. Particularly for highly anisotropic models, we further observe improvements on standard semantic similarity benchmarks, indicating that the calibrated space better captures semantic associations. After calibration, over 30% of WEAT results change significance status, and effect sizes shift in both directions depending on bias category. These shifts suggest that uncalibrated measurements may both overestimate and underestimate the associations encoded in the embedding space. These findings indicate that previously reported bias measurements in anisotropic embedding spaces should be interpreted with caution and may benefit from re-evaluation with calibrated methods. Our approach contributes to restoring the measurement foundation of WEAT across both computational social science and AI fairness research.

Edge Artificial Intelligence (Edge AI) enables the deployment of AI models directly on local edge devices, while such deployments are subject to strict resource constraints, particularly in clinical applications requiring local and timely inference. In such contexts, explainable artificial intelligence (XAI) can serve as a human-AI interface intended to support healthcare professionals' and patients' understanding of model predictions and informed decision-making. To fulfill this role, XAI method selection for TinyML deployments can be formulated as a human-centered multi-objective design problem that jointly considers qualitative stakeholder preferences, explanation quality, and proxy-based deployment cost. We propose a framework that integrates a large language model (LLM)-guided design interface that maps qualitative stakeholder preferences to candidate XAI methods, followed by deterministic feasibility filtering and Pareto-based optimization. The framework exposes trade-offs among explanation fidelity, stability, and proxy-based deployment cost while characterizing their implications for explanation quality and estimated deployment feasibility. A proof-of-concept evaluation on a skin lesion classification task illustrates how the framework systematically compares candidate XAI methods and identifies Pareto-efficient trade-offs. The present evaluation covers the computational selection stages, while physical MCU deployment and empirical human-expert validation remain outside the scope of this study.

Modern AI systems depend on annotated data, but annotation is rarely treated as the act of measurement that it is. Instead, annotation quality is commonly reduced to agreement: if multiple annotators assign the same annotation to a data instance, the annotations are taken to be high-quality. Yet agreement does not establish whether annotations validly capture the underlying concept they are meant to represent. In this paper, we argue that data annotation should be understood as a measurement problem. Like other forms of measurement, annotation requires defining a concept, operationalizing it through an instrument, applying that instrument, and evaluating the reliability and validity of the resulting measurements. Drawing on a literature review of annotation quality research (N=132) and semi-structured interviews with annotation team members (N=10), we develop a framework for diagnosing and correcting annotation issues. First, we map key decision points across annotation processes - including task design, annotator management, quality assessment, quality improvement, and adjudication - that shape annotation outcomes. Second, we identify five distinct sources of annotation issues: error, ambiguity, impossibility, subjectivity, and annotator identity. Annotation problems that appear similar at the level of outcomes often require different process-level interventions based on their sources. Finally, we translate measurement theory into practical guidance for annotation teams, showing how assessments of reliability and validity can move beyond agreement alone. By reframing annotation as measurement, we offer a conceptual foundation for improving the quality of annotated data used in AI research and practice.

As artificial intelligence (AI) systems transition from research prototypes to operational tools in Earth system science and forecasting, establishing trust in their predictions becomes increasingly important. Although model inputs and outputs are observable, the internal decision-making of modern AI models remains complex and hard to interpret, earning them the label ``black boxes.'' Explainable artificial intelligence (XAI) offers techniques to provide insight into these processes. However, most XAI methods were developed for classification tasks, raising questions about their suitability for the regression problems that dominate geoscientific applications. We review XAI approaches through this lens, organising them into a structured framework and examining both their theoretical foundations and practical behaviour. To ground this discussion, we apply a selection of methods to a machine learning emulator of the Lorenz 1963 system, an archetypal chaotic model that provides a tractable, physically meaningful setting for exposing the limitations and failure modes of general-purpose XAI in regression contexts. We then survey how these and related methods have been applied across a variety of Earth system sciences. We further situate XAI within the model development lifecycle, linking methodological choices to the needs of different stakeholder groups across operational Earth system science. We close by identifying gaps in existing methodologies and outlining a forward-looking research agenda, with practical recommendations for the responsible, effective use of XAI in regression applications of geoscientific modelling and forecasting.

Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing approaches such as RLHF, CAI, and their variants have achieved promising results, they often rely on a single-agent framework and a unified reward system. This limits their ability to capture ethical pluralism, adapt to diverse moral contexts, and reflect the dynamics of multi-agent moral reasoning. In this work, we propose a framework that utilizes multilayer combinatorial fusion for contextual value alignment (MCF-CVA). At the first layer of the framework, it instantiates multiple moral agents, each fine-tuned to represent a distinctive value. Their outputs are then expanded combinatorially using both score- and rank-combinations as well as average and weighted aggregations. These combined models are then reduced to the same number of initial moral agents. This expansion and reduction (EAR) process continues for multi-layers until a stopping criterion is reached. The MCF-CVA framework leverages cognitive diversity between agents to mitigate conflicts and redundancies across multiple agents, producing responses that better reflect contextual human values. The framework using the EAR algorithm is performed on the dual architecture of Euclidean score space and Kemeny rank space. Empirical evaluations demonstrated that the proposed framework outperforms single-agent baselines, multi-agent single-layer results, and previous aggregation approaches on standard metrics, showing that the MCF-CVA framework provides a robust and effective mechanism for advancing contextual value alignment in LLMs.

Personalized, generative AI systems increasingly adapt their behavior to individual users over time, fundamentally changing model behavior. While existing auditing approaches have been effective at surfacing harms in non-personalized contexts, they often rely on static, simulated evaluations and definitions of harm that aggregate across broad, group categories. In this position paper, we argue that such approaches can fail to capture emergent harms in personalized generative AI systems, where harms surface through interpretations of ongoing interaction and evolve with user history. We identify three presuppositions underlying many harm auditing paradigms: that harms can be (1) specified outside real-world interaction, (2) defined non-pluralistically within groups, and (3) treated as static. One might argue that personalized systems could simply learn definitions of what constitutes harm to individual users through repeated interactions. However, we argue that attempts to surface user harms through deeper personalization risk imposing asymmetric burdens of labor and privacy on marginalized users. Consequently, we propose reframing understandings of harm as adaptive, user- and community-centered processes, and outline design directions that shift auditing from retrospective evaluation toward infrastructures that support ongoing articulation of harm in interaction. Our work highlights the need for auditing and design practices that better reflect the pluralistic and evolving nature of harm understanding in personalized generative AI systems.

Deep learning models have become integral to security applications due to their ability to model complex relationships in data and detect sophisticated threats. However, their complexity makes it difficult to understand how predictions are generated, posing significant challenges for interpretability, particularly in security applications where transparency is critical. Existing explanation methods, such as visual explanation techniques and post-hoc approaches, suffer from several limitations: reduced faithfulness due to local approximation errors, instability caused by reliance on randomness, and computational inefficiency that hinders real-time usage. To address these issues, we introduce XSec, a self-explainable deep architecture developed for security applications. During training, XSec uses a novel mask-based approach to extract informative sub-features from the data and learns prototypes, representative patterns that characterize each class. XSec then leverages the prototypes in a dedicated similarity layer at test time to compute similarity scores and generates interpretable explanations without the need for post-hoc analysis. We evaluate XSec across five diverse security scenarios, demonstrating its ability to achieve an average classification accuracy of 97.33% with minimal performance compromise. XSec produces deterministic explanations for a fixed trained model and input and substantially reduces explanation latency compared with approximation-based and perturbation-based post-hoc methods. Through this effort, we extend the applicability of self-explainable AI to security applications, bridging the gap between deep learning performance and the need for explainability in critical scenarios.

Epistemic Trustworthiness in Generative AI: A Normative Framework for Warranted Reliance in High-Stakes Workflows

Nimisha Karnatak, Max Van Kleek, Nigel Shadbolt

Generative AI systems are increasingly deployed in high-stakes professional contexts, where their outputs shape what users believe, how they reason, and what they treat as settled. This raises a central question for responsible AI: under what conditions is reliance on generative AI outputs epistemically warranted rather than behaviourally induced? Existing frameworks largely ask whether AI outputs are accurate, fair, explainable, safe, or trusted by users. These questions remain necessary, and each can contribute to warranted reliance. However, they do not directly specify warranted reliance as a distinct evaluative target: the conditions under which users are justified in treating AI outputs as inputs into their own reasoning. We argue that this requires an account of epistemic trustworthiness: what makes a system epistemically worthy of reliance. Drawing on philosophical accounts of trustworthiness as competence and audience-orientation, we develop a constitutive normative framework comprising three jointly necessary and non-fungible conditions. First, epistemic humility requires systems to represent and communicate the limits of their competence. Second, epistemic access requires systems to enable users to inspect, question, and contest outputs in context. Third, resistance to epistemic injustice requires systems to recognise users as legitimate epistemic agents and avoid marginalising their knowledge and experience. Through real-world case analyses in legal reasoning, medical reasoning, and hiring, we show how failures of epistemic humility, epistemic access, and resistance to epistemic injustice can produce consequential harms that standard measures of accuracy, fairness, and usability do not address on their own. We conclude by outlining design and evaluation implications for GenAI systems organised around epistemically warranted reliance rather than output correctness alone.