arXiv subjects

Anthony Rhodes

Publications and source records attributed to Anthony Rhodes.

9 recordsLinked to original sources

arXiv2026

BMMS: Policy-Conditioned Measurement of Behavioral Compliance in Language Models

Behavioral evaluation of language models fixes its dimensions in advance: hallucination, sycophancy, toxicity, over-refusal. An operator in a regulated industry needs a different question answered: does a system do what a particular rulebook requires? We introduce the Behavioral Misalignment Metric Suite (BMMS), which measures policy-conditioned misalignment by taking a policy corpus as an argument and returning a compliance profile over it, for any published policy and any system that answers in natural language. The Compliance Attainment Score (CAS) measures severity-weighted attainment over the obligations that bind the system, and the Compliance Robustness Margin (CRM) the share of that attainment surviving graded adversarial pressure; Behavioral Invariance (BIV) and the Behavioral Disposition Index (BDI) are specified and released with the suite. Dimensions enter only by passing a published admission test whose binding criterion is attribution: a quantity that moves when the judge changes, holding the target fixed, is measuring the instrument. Applying it excluded one of the quantities the suite itself reported. Across 1,003 obligations from eleven documents in five registers, the admission criterion holds 94.4% precision against blinded human judgment on vendor specifications and 50.0% on analytical guidance, extraction fidelity is 94.6%, and re-scoring under judges from two other providers leaves target ordering invariant while the absolute score of a single target spans up to 0.22. We apply it to the two most detailed published behavioral specifications. Own-specification advantage is not resolved from zero once document difficulty is subtracted, but absolute self-compliance is another matter: GPT-4o fails 70.7% of the hard constraints binding it in the Model Spec published by OpenAI, where the two Claude models fail 0.0% and 9.1% of theirs.

cs.AI↗

arXiv2026

Penumbra: Sample-Efficient Adversarial Search for Regulatory Obligations

Agents are entering finance, healthcare and law, sectors where a violation leaves no lexical signature and carries real penalties. Whether an omission is material, or a disclosure sufficient, depends on what the response left out. Probing such an obligation means finding responses one minimal edit from flipping compliance, and every probe costs a generation and two adjudications, so the binding constraint on regulatory red-teaming is sample efficiency, not volume. We introduce Penumbra, an adversarial search that walks from a verified anchor under an expanding edit budget until a two-evaluator committee changes its verdict, and emits the two adjacent responses that straddle the change. Allocation is adaptive, and the objective is coverage of the defeat surface: distinct (obligation x defeat mode) cells resolved per candidate. At matched budget, adaptive allocation reaches uniform allocation's full-budget coverage on 59% of the candidates; at equal records it covers 1.43x the defeat modes of naive enumeration, and the gain is confined to the axis it targets. On 60 screened obligations of a financial advisory constitution, Penumbra returns 144 pairs, each a compliant and a violating response that the committee places on opposite sides of the boundary, differing by a handful of words where a model asked for both directly produces texts sharing almost nothing. A second constitution, for clinical triage, reproduces this on 18 obligations: 49 pairs at the same tightness, with the same modes hardest. Pairs like these show where an obligation's own terms stop deciding, which is what an agent deployed under it must be tested against, and the search finds them at a cost that scales with the boundary, not the text.

cs.AI↗

arXiv2026

Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check

A verifier for an agent faces rules of two kinds: the ones a fixed check can settle and the ones that require a judge. A team that derives its own checks fixes that split up front. Where the requirements come from outside, as in finance, healthcare and law, the agent enforces rules it did not write, so the split falls to runtime, recurring for every predicate of every rule on every action at a rate no reviewer can audit. Every escalation scheme assumes a model can make that decision itself, that it is self-decidable. Across six corpora, including the EU AI Act, FINRA guidance and a deployed credit agent, we collect roughly 22,000 labels from four models built by three labs. They agree almost perfectly where the answer is obvious and collapse on regulatory text; their errors run in opposite directions, so no model can be trusted as the conservative choice; and on the deployed agent's own rule-set they err together, over-claiming that a fixed check will do, the direction that never gets escalated. We introduce CoVer (corroborate-then-verify), which treats unanimity as a nomination, admitting a predicate only when the check synthesized for it survives intervention, reading fields the agent cannot write and holding under deterministic rewording. That gate rejects most of what corroboration wrongly admits, at a cost in coverage we report rather than tune away. The obvious alternative, agreement with a reference judge, certifies nothing: it climbs from 30% to 77% across calibration bands while the genuinely decidable share does not move, because a judge drawn from the population under indictment ratifies the blind spot it shares. Self-decidability is not a capability to elicit from a model but a boundary the verifier must construct.

cs.AI↗

arXiv2025

Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem

As generative models are advancing in quality and quantity for creating synthetic content, deepfakes begin to cause online mistrust. Deepfake detectors are proposed to counter this effect, however, misuse of detectors claiming fake content as real or vice versa further fuels this misinformation problem. We present the first comprehensive uncertainty analysis of deepfake detectors, systematically investigating how generative artifacts influence prediction confidence. As reflected in detectors' responses, deepfake generators also contribute to this uncertainty as their generative residues vary, so we cross the uncertainty analysis of deepfake detectors and generators. Based on our observations, the uncertainty manifold holds enough consistent information to leverage uncertainty for deepfake source detection. Our approach leverages Bayesian Neural Networks and Monte Carlo dropout to quantify both aleatoric and epistemic uncertainties across diverse detector architectures. We evaluate uncertainty on two datasets with nine generators, with four blind and two biological detectors, compare different uncertainty methods, explore region- and pixel-based uncertainty, and conduct ablation studies. We conduct and analyze binary real/fake, multi-class real/fake, source detection, and leave-one-out experiments between the generator/detector combinations to share their generalization capability, model calibration, uncertainty, and robustness against adversarial attacks. We further introduce uncertainty maps that localize prediction confidence at the pixel level, revealing distinct patterns correlated with generator-specific artifacts. Our analysis provides critical insights for deploying reliable deepfake detection systems and establishes uncertainty quantification as a fundamental requirement for trustworthy synthetic media detection.

cs.AI↗

arXiv2024

QA-TOOLBOX: Conversational Question-Answering for process task guidance in manufacturing

In this work we explore utilizing LLMs for data augmentation for manufacturing task guidance system. The dataset consists of representative samples of interactions with technicians working in an advanced manufacturing setting. The purpose of this work to explore the task, data augmentation for the supported tasks and evaluating the performance of the existing LLMs. We observe that that task is complex requiring understanding from procedure specification documents, actions and objects sequenced temporally. The dataset consists of 200,000+ question/answer pairs that refer to the spec document and are grounded in narrations and/or video demonstrations. We compared the performance of several popular open-sourced LLMs by developing a baseline using each LLM and then compared the responses in a reference-free setting using LLM-as-a-judge and compared the ratings with crowd-workers whilst validating the ratings with experts.

cs.CL↗

arXiv2024

Graph Regularized Sparse $L_{2,1}$ Semi-Nonnegative Matrix Factorization for Data Reduction

Non-negative Matrix Factorization (NMF) is an effective algorithm for multivariate data analysis, including applications to feature selection, pattern recognition, and computer vision. Its variant, Semi-Nonnegative Matrix Factorization (SNF), extends the ability of NMF to render parts-based data representations to include mixed-sign data. Graph Regularized SNF builds upon this paradigm by adding a graph regularization term to preserve the local geometrical structure of the data space. Despite their successes, SNF-related algorithms to date still suffer from instability caused by the Frobenius norm due to the effects of outliers and noise. In this paper, we present a new $L_{2,1}$ SNF algorithm that utilizes the noise-insensitive $L_{2,1}$ norm. We provide monotonic convergence analysis of the $L_{2,1}$ SNF algorithm. In addition, we conduct numerical experiments on three benchmark mixed-sign datasets as well as several randomized mixed-sign matrices to demonstrate the performance superiority of $L_{2,1}$ SNF over conventional SNF algorithms under the influence of Gaussian noise at different levels.

math.NA↗

arXiv2023

My Art My Choice: Adversarial Protection Against Unruly AI

Generative AI is on the rise, enabling everyone to produce realistic content via publicly available interfaces. Especially for guided image generation, diffusion models are changing the creator economy by producing high quality low cost content. In parallel, artists are rising against unruly AI, since their artwork are leveraged, distributed, and dissimulated by large generative models. Our approach, My Art My Choice (MAMC), aims to empower content owners by protecting their copyrighted materials from being utilized by diffusion models in an adversarial fashion. MAMC learns to generate adversarially perturbed "protected" versions of images which can in turn "break" diffusion models. The perturbation amount is decided by the artist to balance distortion vs. protection of the content. MAMC is designed with a simple UNet-based generator, attacking black box diffusion models, combining several losses to create adversarial twins of the original artwork. We experiment on three datasets for various image-to-image tasks, with different user control values. Both protected image and diffusion output results are evaluated in visual, noise, structure, pixel, and generative spaces to validate our claims. We believe that MAMC is a crucial step for preserving ownership information for AI generated content in a flawless, based-on-need, and human-centric way.

cs.CV↗

arXiv2022

Distill and Collect for Semi-Supervised Temporal Action Segmentation

Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is available. In contrast, we can easily collect a large corpus of in-domain unannotated videos by scavenging through the internet. Thus, this paper proposes an approach for the temporal action segmentation task that can simultaneously leverage knowledge from annotated and unannotated video sequences. Our approach uses multi-stream distillation that repeatedly refines and finally combines their frame predictions. Our model also predicts the action order, which is later used as a temporal constraint while estimating frames labels to counter the lack of supervision for unannotated videos. In the end, our evaluation of the proposed approach on two different datasets demonstrates its capability to achieve comparable performance to the full supervision despite limited annotation.

cs.CV↗

arXiv2022

Human in the loop approaches in multi-modal conversational task guidance system development

Development of task guidance systems for aiding humans in a situated task remains a challenging problem. The role of search (information retrieval) and conversational systems for task guidance has immense potential to help the task performers achieve various goals. However, there are several technical challenges that need to be addressed to deliver such conversational systems, where common supervised approaches fail to deliver the expected results in terms of overall performance, user experience and adaptation to realistic conditions. In this preliminary work we first highlight some of the challenges involved during the development of such systems. We then provide an overview of existing datasets available and highlight their limitations. We finally develop a model-in-the-loop wizard-of-oz based data collection tool and perform a pilot experiment.

cs.CL↗