The paper proposes a new method for evaluating AI accountability by analyzing the structural quality of a model’s defense for its decisions, using a four‑phase dialectical protocol based on Walton’s argumentation schemes and Govier’s criteria. Applied to nine large language models and 200 ambiguous moral-choice items, the study finds that models generally defend their reasoning well above the rubric minimum, though failures cluster on grounds and sufficiency and correlate with epistemic hedging. The protocol also reveals that models often present different argument schemes in justification than in reasoning, detects indefensible defenses, and highlights challenges in assessing retraction in AI alignment.
By Daan R. Henselmans, Derck W. E. Prinzhorn, Arno Libert
arXiv:2608. 05602v1 Announce Type: new Abstract: 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.
By Nimisha Karnatak, Max Van Kleek, Nigel Shadbolt
arXiv:2608. 15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations.
By Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana, Helen Nissenbaum
The paper argues that as AI systems increasingly generate code, the bottleneck has shifted to supervising these systems, revealing a vocabulary gap between cybernetic coordination (actions aligning with the world) and epistemic coordination (understanding that can be verified). It critiques current oversight that merely approves outputs, proposing instead that every consequential choice by an agent must include a retrievable condition explaining why it was made, enabling third‑party verification. The authors illustrate this with three delegation episodes, introduce a two‑part reconstruction test, and propose the ORRCF convention to embed such conditions in all recorded decisions.
By J\'er\'emie Lumbroso
arXiv:2607. 24391v1 Announce Type: cross Abstract: AI systems already govern.
By Gilad Abiri
arXiv:2608.28593v1 Announce Type: new
Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in...
By Cindy Delage, St\'ephane Canu, Marc D\'ecombas, Jonathan Foureur
The article argues that generative AI embeds the majority’s way of knowing as the default infrastructure of knowledge, a phenomenon termed epistemic subordination. This occurs because the training process compresses diverse human expression into a single probabilistic model whose baseline reflects dominant cultural languages, assumptions, and frameworks. Minority epistemologies are absorbed but structurally subordinated in the output, creating a unified harm that spans anti‑discrimination law, cultural and linguistic rights, and democratic viewpoint pluralism, and the author contends that legal remedies must target the training stage rather than downstream decisions.
By Gilad Abiri, Emanuel V. Towfigh
arXiv:2606. 12437v1 Announce Type: cross Abstract: The increasing encroachment of artificial intelligence (AI) on social life raises significant risks for society, particularly within the infospheres created and controlled by companies such as Google, Facebook, Apple, and Amazon.
By Oren Perez, Nurit Wimer
arXiv:2606. 30116v1 Announce Type: new Abstract: Pairwise preference data is widely used for training and evaluating language models (e.
By Eleanor Clifford, Michael Amir, Arduin Findeis, Aaron Zhao, Robert Mullins
The paper examines how large language model (LLM) outputs are increasingly used in contexts that demand justified interpretations, such as law, education, policy analysis, and public moral debate. It identifies a recurring failure—interpretive misplacement—where model-generated readings are treated as settled meanings without explicit interpretive frames, provenance, or defensible alternatives, leading to accountability loss. Drawing on philosophical hermeneutics, the author proposes design principles for human‑AI co‑interpretation, reorganizes existing LLM techniques into hermeneutically responsible patterns, and discusses implications for legal practice, education, scholarship, and public discourse, while framing digital hermeneutics as a literacy for critically engaging with AI‑mediated texts.
By Behrooz Razeghi
arXiv:2603. 28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.
By Camilo Chac\'on Sartori
As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relies on natural-language prose: a...