Research

Papers

Research papers from arXiv and related sources

Total: 4513 AI/LLM: 2483 Testing: 2030
TESTING

A variational multi-phase model for elastoplastic materials with microstructure evolution

A general model is formulated for elasto-plastic materials undergoing linear kinematic hardening to describe microstructure evolution associated with phase transformations. Using infinitesimal stra...

Sarah Dinkelacker-Steinhoff, Klaus Hackl

2602.17492 2026-02-19
AI LLM

What Do LLMs Associate with Your Name? A Human-Centered Black-Box Audit of Personal Data

Large language models (LLMs), and conversational agents based on them, are exposed to personal data (PD) during pre-training and during user interactions. Prior work shows that PD can resurface, ye...

Dimitri Staufer, Kirsten Morehouse

2602.17483 2026-02-19
AI LLM

ShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality

Augmented Reality (AR) can simulate various visual perceptions, such as how individuals with colorblindness see the world. However, these simulations require developers to predefine each visual eff...

Yanni Mei, Samuel Wendt, Florian Mueller, Jan Gugenheimer

2602.17481 2026-02-19
AI LLM

Small LLMs for Medical NLP: a Systematic Analysis of Few-Shot, Constraint Decoding, Fine-Tuning and Continual Pre-Training in Italian

Large Language Models (LLMs) consistently excel in diverse medical Natural Language Processing (NLP) tasks, yet their substantial computational requirements often limit deployment in real-world hea...

Pietro Ferrazzi, Mattia Franzin, Alberto Lavelli, Bernardo Magnini

2602.17475 2026-02-19
TESTING

Optically Sensorized Electro-Ribbon Actuator (OS-ERA)

Electro-Ribbon Actuators (ERAs) are lightweight flexural actuators that exhibit ultrahigh displacement and fast movement. However, their embedded sensing relies on capacitive sensors with limited p...

Carolina Gay, Petr Trunin, Diana Cafiso, Yuejun Xu, Majid Taghavi, Lucia Beccai

2602.17474 2026-02-19
AI LLM

Auditing Reciprocal Sentiment Alignment: Inversion Risk, Dialect Representation and Intent Misalignment in Transformers

The core theme of bidirectional alignment is ensuring that AI systems accurately understand human intent and that humans can trust AI behavior. However, this loop fractures significantly across lan...

Nusrat Jahan Lia, Shubhashis Roy Dipta

2602.17469 2026-02-19
AI LLM

Entropy-Based Data Selection for Language Models

Modern language models (LMs) increasingly require two critical resources: computational resources and data resources. Data selection techniques can effectively reduce the amount of training data re...

Hongming Li, Yang Liu, Chao Huang

2602.17465 2026-02-19
AI LLM

The CTI Echo Chamber: Fragmentation, Overlap, and Vendor Specificity in Twenty Years of Cyber Threat Reporting

Despite the high volume of open-source Cyber Threat Intelligence (CTI), our understanding of long-term threat actor-victim dynamics remains fragmented due to the lack of structured datasets and inc...

Manuel Suarez-Roman, Francesco Marciori, Mauro Conti, Juan Tapiador

2602.17458 2026-02-19
TESTING

Privacy in Theory, Bugs in Practice: Grey-Box Auditing of Differential Privacy Libraries

Differential privacy (DP) implementations are notoriously prone to errors, with subtle bugs frequently invalidating theoretical guarantees. Existing verification methods are often impractical: form...

Tudor Cebere, David Erb, Damien Desfontaines, Aurélien Bellet, Jack Fitzsimons

2602.17454 2026-02-19
AI LLM

Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge

We present Jolt Atlas, a zero-knowledge machine learning (zkML) framework that extends the Jolt proving system to model inference. Unlike zkVMs (zero-knowledge virtual machines), which emulate CPU ...

Wyatt Benno, Alberto Centelles, Antoine Douchet, Khalil Gibran

2602.17452 2026-02-19
AI LLM

Beyond Pipelines: A Fundamental Study on the Rise of Generative-Retrieval Architectures in Web Research

Web research and practices have evolved significantly over time, offering users diverse and accessible solutions across a wide range of tasks. While advanced concepts such as Web 4.0 have emerged f...

Amirereza Abbasi, Mohsen Hooshmand

2602.17450 2026-02-19
AI LLM

ACOS: Arrays of Cheap Optical Switches

Machine learning training places immense demands on cluster networks, motivating specialized architectures and co-design with parallelization strategies. Recent designs incorporating optical circui...

Daniel Amir, Ori Cohen, Jakob Krebs, Mark Silberstein

2602.17449 2026-02-19
AI LLM

Do Hackers Dream of Electric Teachers?: A Large-Scale, In-Situ Evaluation of Cybersecurity Student Behaviors and Performance with AI Tutors

To meet the ever-increasing demands of the cybersecurity workforce, AI tutors have been proposed for personalized, scalable education. But, while AI tutors have shown promise in introductory progra...

Michael Tompkins, Nihaarika Agarwal, Ananta Soneji, Robert Wasinger, Connor Nelson, Kevin Leach, ...

2602.17448 2026-02-19
AI LLM

ABCD: All Biases Come Disguised

Multiple-choice question (MCQ) benchmarks have been a standard evaluation practice for measuring LLMs' ability to reason and answer knowledge-based questions. Through a synthetic NonsenseQA benchma...

Mateusz Nowak, Xavier Cadet, Peter Chin

2602.17445 2026-02-19
AI LLM

AIDG: Evaluating Asymmetry Between Information Extraction and Containment in Multi-Turn Dialogue

Evaluating the strategic reasoning capabilities of Large Language Models (LLMs) requires moving beyond static benchmarks to dynamic, multi-turn interactions. We introduce AIDG (Adversarial Informat...

Adib Sakhawat, Fardeen Sadab, Rakin Shahriar

2602.17443 2026-02-19
AI LLM

WarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation

Innovation in Recommender Systems is currently impeded by a fractured ecosystem, where researchers must choose between the ease of in-memory experimentation and the costly, complex rewriting requir...

Marco Avolio, Potito Aghilar, Sabino Roccotelli, Vito Walter Anelli, Chiara Mallamaci, Vincenzo P...

2602.17442 2026-02-19
AI LLM

Preserving Historical Truth: Detecting Historical Revisionism in Large Language Models

Large language models (LLMs) are increasingly used as sources of historical information, motivating the need for scalable audits on contested events and politically charged narratives in settings t...

Francesco Ortu, Joeun Yook, Punya Syon Pandey, Keenan Samway, Bernhard Schölkopf, Alberto Cazzani...

2602.17433 2026-02-19
AI LLM

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study

Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are largely designed for short-form outputs and do not generali...

Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj, David Skarbrevik

2602.17431 2026-02-19
AI LLM

Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metrics

Evaluating machine translation (MT) quality in extremely low-resource language (ELRL) scenarios poses unique challenges, as widely used metrics such as BLEU, effective in high-resource settings, of...

Sanjeev Kumar, Preethi Jyothi, Pushpak Bhattacharyya

2602.17425 2026-02-19
AI LLM

Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking

We investigate the convergence guarantee of two-layer neural network training with Gaussian randomly masked inputs. This scenario corresponds to Gaussian dropout at the input level, or noisy input ...

Afroditi Kolomvaki, Fangshuo Liao, Evan Dramko, Ziyun Guang, Anastasios Kyrillidis

2602.17423 2026-02-19