paper-with-me

홈 › Papers

Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance

2026-09-09 · Samar Ansari arxiv

Compute governance today is a governance of training: the thresholds, reporting requirements, and frontier-AI regimes now in force attach to training compute and treat the trained model as the regulatory unit. That picture is incomplete: capability increasingly migrates to the deployment stage through inference-time scaling, agentic scaffolding, and compression onto consumer hardware. This paper asks which mechanisms are available once the regulatory object shifts from the training run to the inference call. We develop a feasibility taxonomy of twenty inference-time mechanisms across monitoring, verification, and enforcement, each rated on a four-point readiness scale against a documented four-vendor evidence base. We then stress the taxonomy against a two-dimensional adversary model (three capability tiers crossed with four adversary roles) and map each mechanism to four governance scenarios (domestic regulation, bilateral or multilateral coordination, industry self-regulation, and compute-marketplace governance). Fifteen of the twenty mechanisms have commercial technical substrates in production today, although governance-grade assurance and adversarial robustness vary substantially. The adversary analysis shows that this readiness holds only against a cooperative deployer and a low-to-medium-capability user: no mechanism rates adequate against a high-capability state-level deployer, and fine-tuning removes the model-internal components of the enforcement cluster, although platform-external controls can persist. A substitution analysis connects the taxonomy to a companion hardware paper as a conditional substitution principle describing when inference-stage and hardware-stage mechanisms provide comparable regulatory coverage under stated conditions. A second-rater reliability check on a random subset of the readiness ratings returned a quadratic-weighted Cohen's kappa of 0.74.

📄 PDF Abstract BibTeX arXiv:2609.10105

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Position: Privacy Is Not Just Memorization!

2025-10-02 · Niloofar Mireshghallah, Tianshi Li arxiv

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underex…

Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers

2026-05-18 · Soheyl Massoudi, Gabriel Apaza, Milad Habibi, Mark Fuge arxiv

Large language models (LLMs) typically approach combinatorial optimization as an inference-time procedure, solving each instance separately through sampling, search, or repeated prompting. We ask whether reinforcement le…

Reinforcement Learning

Multilingual Detection of Alzheimer's Disease from Speech: A Cross-Linguistic Transfer Learning Approach

2026-06-04 · Nadine Yasser Abdelhalim, Emmanuel Akinrintoyo, Nicole Salomons arxiv

The development of multilingual Alzheimer's Disease Dementia (AD) detection models presents significant challenges due to the resource-intensive and time-consuming nature of language-specific model training. We propose a…

Transfer Learning

Learning to Place Guards by Reinforcement: A Geo-Free Neural Policy for the Vertex-Guard Art Gallery Problem

2026-06-19 · Domagoj Ševerdija, Jurica Maltar, Nathan Chappel, Domagoj Matijević arxiv

Neural combinatorial optimization (NCO) has shown that policies trained by reinforcement can construct strong solutions to NP-hard problems directly from raw instances. What such a policy actually learns, as opposed to w…

Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy

2024-02-20 · Liyan Xu, Zhenlin Su, Mo Yu, Jin Xu 외

Factual inconsistencies pose a significant hurdle for the faithful summarization by generative models. While a major direction to enhance inconsistency detection is to derive stronger Natural Language Inference (NLI) mod…

Language ModellingLarge Language ModelNatural Language InferenceQuestion Generation+1