arXiv subjects

Angelie Kraft

Publications and source records attributed to Angelie Kraft.

5 recordsLinked to original sources

arXiv2026

The Benchmark Trap: Structures of Power and Injustice in AI Evaluations

Artificial intelligence (AI) benchmarks are not neutral tools of evaluation but socio-technical artefacts that shape competition, power, and research priorities within AI. Benchmarks standardise the assessment of systems and facilitate the creation of leaderboards that reward state-of-the-art performance with prestige, citations, trust, and institutional influence. As the costs of developing competitive AI systems rise, these rewards increasingly concentrate among powerful, industry-funded labs. This paper situates these concerns within Iris Marion Young's theories of oppression and structural injustice. It argues that current benchmarking practices may perpetuate systematic harms affecting various actors in AI research, aligning with four of Young's "faces of oppression". Benchmarking culture is further framed as a source of structural injustice, as these harms emerge from normalised, individually defensible practices and network effects, even without explicit wrongdoing. By reinforcing existing power structures and narrowing possible research trajectories, benchmarking may in fact prevent the field from advancing in epistemically robust and socially beneficial ways.

cs.AI↗

arXiv2026

Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure

Perspective API closes at the end of 2026, removing the de facto standard for toxicity measurement and exposing researchers' dependence on a tool they did not control. Drawing on this case, we argue that a research field must build and govern its own measurement infrastructure rather than borrow it. Surveying 241 papers that use or study Perspective, we show what depending on it cost the research community: claims reaching past what the tool could support, results that shifted when its model was silently retrained, and disparities researchers could measure but not explain. These failures were amplified throughout the LLM lifecycle, where Perspective supplied the labels, filtered the corpora, and graded the systems trained on each, rewarding errors rather than catching them. To keep the instrument open to study after shutdown, we release Perspective scores for 5.9 million text snippets from 77 datasets. We further specify ten requirements for measurement infrastructure a field owns, and argue that what blocks such infrastructure is not technical capability but the value the field places on infrastructure work.

cs.CL↗

arXiv2026

Social Bias in Popular Question-Answering Benchmarks

Question-answering (QA) and reading comprehension (RC) benchmarks are commonly used for assessing the capabilities of large language models (LLMs) to retrieve and reproduce knowledge. However, we demonstrate that popular QA and RC benchmarks do not cover questions about different demographics or regions in a representative way. We perform a content analysis of 30 benchmark papers and a quantitative analysis of 20 respective benchmark datasets to learn (1) who is involved in the benchmark creation, (2) whether the benchmarks exhibit social bias, or whether this is addressed or prevented, and (3) whether the demographics of the creators and annotators correspond to particular biases in the content. Most benchmark papers analyzed provide insufficient information about those involved in benchmark creation, particularly the annotators. Notably, just one (WinoGrande) explicitly reports measures taken to address social representation issues. Moreover, the data analysis revealed gender, religion, and geographic biases across a wide range of encyclopedic, commonsense, and scholarly benchmarks. Our work adds to the mounting criticism of AI evaluation practices and shines a light on biased benchmarks being a potential source of LLM bias by incentivizing biased inference heuristics.

cs.CL↗

arXiv2022

The Ethical Risks of Analyzing Crisis Events on Social Media with Machine Learning

Social media platforms provide a continuous stream of real-time news regarding crisis events on a global scale. Several machine learning methods utilize the crowd-sourced data for the automated detection of crises and the characterization of their precursors and aftermaths. Early detection and localization of crisis-related events can help save lives and economies. Yet, the applied automation methods introduce ethical risks worthy of investigation - especially given their high-stakes societal context. This work identifies and critically examines ethical risk factors of social media analyses of crisis events focusing on machine learning methods. We aim to sensitize researchers and practitioners to the ethical pitfalls and promote fairer and more reliable designs.

cs.LG↗

arXiv2022

The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs

Knowledge graphs are increasingly used in a plethora of downstream tasks or in the augmentation of statistical models to improve factuality. However, social biases are engraved in these representations and propagate downstream. We conducted a critical analysis of literature concerning biases at different steps of a knowledge graph lifecycle. We investigated factors introducing bias, as well as the biases that are rendered by knowledge graphs and their embedded versions afterward. Limitations of existing measurement and mitigation strategies are discussed and paths forward are proposed.

cs.CL↗