The paper introduces BiasGuard‑D, a system that uses two adversarial language‑model agents from different families to exchange typed claim documents, with a third model quorum voting to adjudicate. A combined referential‑plus‑semantic invariant validates the verdict, and the iterative deliberation layer shifts remediation from stereotypes to hallucinations, improving right‑answer recovery by 49 percentage points on HaluEval QA. All claims, votes, and instructions are stored as typed records, providing an auditable provenance trail for operators under emerging AI regulations.
By Kardelen Subasi, Jaros{\l}aw A. Chudziak
arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.
By Niraj Kumar, Harsh Kasyap
arXiv:2606. 02198v1 Announce Type: new Abstract: Prediction tasks over individual futures, which are inherently noisy, often admit multiple similarly accurate models.
By Ashwin Singh, Carlos Castillo
LLM-generated records increasingly populate production information systems where they are treated as data assets subject to the same quality expectations as records from operational databases. A singl...
arXiv:2608. 04365v1 Announce Type: new Abstract: Audits have emerged as a critical instrument for algorithmic governance, providing a mechanism for external scrutiny and governance of machine learning models.
By Augustin Godinot, Sofiane Azogagh, Julien Ferry, S\'ebastien Gambs
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
By Qiqi Liu, Runhan Song, Shilin Ye
arXiv:2604. 08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization.
By Niklas Herbster, Martin Zborowski, Alberto Tosato, Gauthier Gidel, Tommaso Tosato
arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.
By Shawn Li, Yue Zhao
arXiv:2610.10199v1 Announce Type: new
Abstract: Emerging legislation requires large language models (LLMs) to be audited for compliance with regulatory standards, particularly fairness. Such black-bo...
By Sayan Biswas, Jade Garcia Bourr\'ee, Anne-Marie Kermarrec, Palak, Martijn de Vos
The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.
By Ye Chen, Weining Zhang
arXiv:2608.21606v1 Announce Type: new
Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whet...
By Ayush Gupta, Hima Varshini Surisetty, Sreevidya Bollineni, Varad Ingale, Tuhina Tripathi, Abhishek Lalwani, Somya Chatterjee, Sadid Hasan
arXiv:2609.40034v1 Announce Type: cross
Abstract: Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM)...
By Ayoub Ajarra, Debabrota Basu