arXiv subjects

Wm. Matthew Kennedy

Publications and source records attributed to Wm. Matthew Kennedy.

9 recordsLinked to original sources

arXiv2026

Toward Human Rights Benchmarking for LLMs: A Pilot Methodology

Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether they can reason correctly about human rights law. To this end, we report our efforts to develop a robust and scalable methodology for creating HumRightsBench: the first expert-validated, scenario-based benchmark for evaluating reasoning grounded in the obligation structure of international human rights law. We adapt the IRAC framework for legal reasoning to better suit the unique reasoning patterns of human rights work (substituting P, "proposing remedies," for C, "legal conclusion," yielding IRAP) to structure our evaluation heuristics. We also produce a pilot series of authentic scenarios designed to implicate the many dimensions of real-world human rights issues and annotated by human rights lawyers and professionals across the world. Ultimately, we find that model accuracy scores range considerably across legal reasoning tasks (overall model performance ranges from 0.339 to 0.577, task min-max ranges from 0.025 to 0.774), which strongly implies that HumRightsBench is a capable instrument for advancing this emerging subfield of AI evaluations science at a critical moment in its evolution.

cs.LG↗

arXiv2026

L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education

Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI applications. We introduce L2-Bench, an open-source benchmark of 1,000+ task-response pairs to aid the pedagogy-led evaluation of LLM capabilities relating to language learning and assessment. Crucially, L2-Bench measures model performativity on the application of learning experience design principles rather than mere knowledge of those principles or broad learning outcomes. Our contributions include: (1) a validated taxonomy of 12 competencies and 31 subcompetencies validated by 200+ expert practitioners (task authenticity: 4.42/5.00, criteria adequacy: 4.18/5.00); (2) a rubric-based evaluation methodology that we believe can, if adapted, generalize to similar (open-ended, qualitative) disciplines; (3) an evaluation dataset that produces reliable signal about model strengths, weaknesses, and contextual robustness across diverse L2 education scenarios. We find that, among large models, Claude Opus 4.7 performs best overall (85.5%), though is marginally outperformed on several constituent tasks. We also find that performance drops notably on harder tasks (69.9% to 73.4%). L2-Bench provides education stakeholders better methods to make more informed decisions about real-world AIED adoption, use, and governance, while advancing the maturing science of AI evaluations for education.

cs.CY↗

arXiv2026

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

cs.AI↗

arXiv2026

Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting

AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers cannot reliably compare results across sources, identify what a report omits, or trace an aggregate claim to its underlying evidence. Recent efforts address isolated components but leave three gaps: they cover only narrow slices of the evaluation lifecycle and do not compose into a single interpretable record; they specify static representations that do not differentiate the questions different stakeholders bring to the same evidence; and they remain proposals on paper, lacking the extraction infrastructure required for adoption at scale. We present \EvalCards{}, an operational reporting layer that composes benchmark metadata, evaluation run data, and model metadata into a unified record. We (1) derive a reporting schema from a structured review of 52 papers and 10 stakeholder interviews, (2) implement four interpretive signals (reproducibility, documentation completeness, provenance and risk, and score comparability), rendered through reader modes calibrated to research and non-research audiences, and (3) deploy a monitoring tool that applies \EvalCards{} across 5,816 models, 635 benchmarks, and 101,843 results, surfacing systematic gaps in current reporting practice.

cs.AI↗

arXiv2026

Towards an Evaluation Methodology for AI in Second Language Education: Lessons Learned from Developing L2-Bench

The rapid adoption of large language models in AI-powered language education has created an urgent need for evaluations that assess pedagogical effectiveness, particularly in language learning--one of the most common LLM use cases (Tamkin et al. 2024; Costa-Gomes et al. 2025). With only narrowly defined task-specific evaluations of AI system capabilities in second language (L2) education existing in the literature, we require more holistic approaches in this AI for education space. To address this gap, we describe the iteration of the methodology we developed to build L2-Bench, a novel, context-specific evaluation benchmark grounded in a validated "language learning experience designer" construct to assess AI capabilities across L2 education contexts. Our methodology integrates pedagogical theory, sociotechnical AI evaluation methods, and operationalizes a hierarchical taxonomy to structure an expert-curated dataset of over 1,000 authentic rubric-scored task-response pairs with measurement and scoring pipeline. We report the results of a pilot validation exercise (N = 39) on an initial sample of our dataset (tasks were validated as authentic [M = 4.23/5], but criteria scores were lower [M = 3.94], with universally poor inter-annotator agreement despite good internal consistency), alongside the experimental design for our follow-up practitioner data validation study as we iterate and scale to the full dataset. Ultimately, this research not only offers methodological lessons towards a more context-specific AI evaluations ecosystem, but also works towards better design of reproducible evaluations for AI systems deployed to educational contexts

cs.CY↗

arXiv2026

Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems

AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially reinforcing misconceptions and eroding learning outcomes over extended use. We present a portion of L2-Bench, a benchmark for evaluating AI systems in language education that includes (but is not limited to) six critical dimensions of effective feedback: diagnostic accuracy, awareness of appropriacy, causes of error, prioritisation, guidance for improvement, and supporting self-regulation. We analyse how AI systems can fail with respect to these dimensions. These failures, which we argue are conducive to "explainability pitfalls," are AI-generated explanations that appear helpful on the surface but are fundamentally flawed, increasing the risk of attainment, human-AI interaction, and socioaffective harms. We discuss how the specific context of language learning amplifies these risks and outline open questions we believe merit more attention when designing evaluation frameworks specifically. Our analysis aims to expand the community's understanding of both the typology of explainability pitfalls and the contextual dynamics in which they may occur in order to encourage AI developers to better design safe, trustworthy, and effective AI explanations.

cs.HC↗

arXiv2025

Ask What Your Country Can Do For You: Towards a Public Red Teaming Model

AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of systems design have developed several effective sociotechnical AI evaluation and red teaming techniques targeting bias, hate speech, mis/disinformation, and other documented harm classes. However, as increasingly sophisticated AI systems are released into high-stakes sectors (such as education, healthcare, and intelligence-gathering), our current evaluation and monitoring methods are proving less and less capable of delivering effective oversight. In order to actually deliver responsible AI and to ensure AI's harms are fully understood and its security vulnerabilities mitigated, pioneering new approaches to close this "responsibility gap" are now more urgent than ever. In this paper, we propose one such approach, the cooperative public AI red-teaming exercise, and discuss early results of its prior pilot implementations. This approach is intertwined with CAMLIS itself: the first in-person public demonstrator exercise was held in conjunction with CAMLIS 2024. We review the operational design and results of this exercise, the prior National Institute of Standards and Technology (NIST)'s Assessing the Risks and Impacts of AI (ARIA) pilot exercise, and another similar exercise conducted with the Singapore Infocomm Media Development Authority (IMDA). Ultimately, we argue that this approach is both capable of delivering meaningful results and is also scalable to many AI developing jurisdictions.

cs.CY↗

arXiv2025

Cascade! Human in the loop shortcomings can increase the risk of failures in recommender systems

Recommender systems are among the most commonly deployed systems today. Systems design approaches to AI-powered recommender systems have done well to urge recommender system developers to follow more intentional data collection, curation, and management procedures. So too has the "human-in-the-loop" paradigm been widely adopted, primarily to address the issue of accountability. However, in this paper, we take the position that human oversight in recommender system design also entails novel risks that have yet to be fully described. These risks are "codetermined" by the information context in which such systems are often deployed. Furthermore, new knowledge of the shortcomings of "human-in-the-loop" practices to deliver meaningful oversight of other AI systems suggest that they may also be inadequate for achieving socially responsible recommendations. We review how the limitations of human oversight may increase the chances of a specific kind of failure: a "cascade" or "compound" failure. We then briefly explore how the unique dynamics of three common deployment contexts can make humans in the loop more likely to fail in their oversight duties. We then conclude with two recommendations.

cs.IR↗

arXiv2024

Vernacularizing Taxonomies of Harm is Essential for Operationalizing Holistic AI Safety

Operationalizing AI ethics and safety principles and frameworks is essential to realizing the potential benefits and mitigating potential harms caused by AI systems. To that end, actors across industry, academia, and regulatory bodies have created formal taxonomies of harm to support operationalization efforts. These include novel holistic methods that go beyond exclusive reliance on technical benchmarking. However, our paper argues that such taxonomies must also be transferred into local categories to be readily implemented in sector-specific AI safety operationalization efforts, and especially in underresourced or high-risk sectors. This is because many sectors are constituted by discourses, norms, and values that "refract" or even directly conflict with those operating in society more broadly. Drawing from emerging anthropological theories of human rights, we propose that the process of "vernacularization"--a participatory, decolonial practice distinct from doctrinary "translation" (the dominant mode of AI safety operationalization)--can help bridge this gap. To demonstrate this point, we consider the education sector, and identify precisely how vernacularizing a leading holistic taxonomy of harm leads to a clearer view of how harms AI systems may cause are substantially intensified when deployed in educational spaces. We conclude by discussing the generalizability of vernacularization as a useful AI safety methodology.

cs.CY↗