arXiv subjects

Jeremy Werner

Publications and source records attributed to Jeremy Werner.

3 recordsLinked to original sources

arXiv2025

Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support

We introduce an Agent-in-the-Loop (AITL) framework that implements a continuous data flywheel for iteratively improving an LLM-based customer support system. Unlike standard offline approaches that rely on batch annotations, AITL integrates four key types of annotations directly into live customer operations: (1) pairwise response preferences, (2) agent adoption and rationales, (3) knowledge relevance checks, and (4) identification of missing knowledge. These feedback signals seamlessly feed back into models' updates, reducing retraining cycles from months to weeks. Our production pilot involving US-based customer support agents demonstrated significant improvements in retrieval accuracy (+11.7% recall@75, +14.8% precision@8), generation quality (+8.4% helpfulness) and agent adoption rates (+4.5%). These results underscore the effectiveness of embedding human feedback loops directly into operational workflows to continuously refine LLM-based customer support system.

cs.AI↗

arXiv2023

A Survey of Data Security: Practices from Cybersecurity and Challenges of Machine Learning

Machine learning (ML) is increasingly being deployed in critical systems. The data dependence of ML makes securing data used to train and test ML-enabled systems of utmost importance. While the field of cybersecurity has well-established practices for securing information, ML-enabled systems create new attack vectors. Furthermore, data science and cybersecurity domains adhere to their own set of skills and terminologies. This survey aims to present background information for experts in both domains in topics such as cryptography, access control, zero trust architectures, homomorphic encryption, differential privacy for machine learning, and federated learning to establish shared foundations and promote advancements in data security.

cs.CR↗

arXiv2011

Measurements of Inclusive W/Z Production Cross Sections at CMS and W/Z as a Luminometer

Leptonic decays of W/Z bosons provide the first electroweak precision measurements at the Large Hadron Collider (LHC). The results of measurements of inclusive W and Z boson production cross sections in pp collisions at $\sqrt{s}=7 \mathrm{TeV}$ are presented, based on 2.9 pb$^{-1}$ of data recorded by the Compact Muon Solenoid (CMS) detector at the LHC. The measurements, performed in the electron and muon decay channels, are combined to give $σ(\mathrm{pp} \rightarrow \mathrm{W}X) \times {\cal{B}}(\mathrm{W} \rightarrow \ell ν) = 9.95\pm0.07\,{\textrm{(stat.)}}\pm 0.28\,{\textrm{(syst.)}}\pm1.09\,{\textrm{(lumi.)}} \mathrm{nb}$ and $σ(\mathrm{pp} \rightarrow \mathrm{Z}X) \times {\cal{B}}(\mathrm{Z} \rightarrow \ell^+ \ell^-) = 0.931\pm0.026\,{\textrm{(stat.)}}\pm 0.023\,{\textrm{(syst.)}}\pm0.102\,{\textrm{(lumi.)}} \mathrm{nb}$, where $\ell$ stands for either $\mathrm{e}$ or $μ$. Theoretical predictions, calculated at the next-to-next-to-leading order (NNLO) in QCD using recent parton distribution functions (PDFs), are in agreement with the measured cross sections. Hence copious production of these well understood and clean signatures suggest the use of W/Z as a "standard candle" for measuring the luminosity at the LHC alongside the current Van der Meer (VdM) separation scan method.

hep-ex↗