arXiv subjects

Stephen Liu

Publications and source records attributed to Stephen Liu.

5 recordsLinked to original sources

arXiv2026

SourceBench: Can AI Answers Reference Quality Web Sources?

Large language models (LLMs) increasingly answer queries by citing web sources, but existing evaluations emphasize answer correctness rather than evidence quality. We introduce SourceBench, a benchmark for measuring the quality of cited web sources across 100 real-world queries spanning informational, factual, argumentative, social, and shopping intents. SourceBench uses an eight-metric framework covering content quality (content relevance, factual accuracy, objectivity) and page-level signals (e.g., freshness, authority/accountability, clarity), and includes a human-labeled dataset with a calibrated LLM-based evaluator that matches expert judgments closely. We evaluate eight LLMs, Google Search, and three AI search tools over 3996 cited sources using SourceBench and conduct further experiments to understand the evaluation results. Overall, our work reveals four key new insights that can guide future research in the direction of GenAI and web search.

cs.AI↗

arXiv2026

OnePiece: A Large-Scale Distributed Inference System with RDMA for Complex AI-Generated Content (AIGC) Workflows

The rapid growth of AI-generated content (AIGC) has enabled high-quality creative production across diverse domains, yet existing systems face critical inefficiencies in throughput, resource utilization, and scalability under concurrent workloads. This paper introduces OnePiece, a large-scale distributed inference system with RDMA optimized for multi-stage AIGC workflows. By decomposing pipelines into fine-grained microservices and leveraging one-sided RDMA communication, OnePiece significantly reduces inter-node latency and CPU overhead while improving GPU utilization. The system incorporates a novel double-ring buffer design to resolve deadlocks in RDMA-aware memory access without CPU involvement. Additionally, a dynamic Node Manager allocates resources elastically across workflow stages in response to real-time load. Experimental results demonstrate that OnePiece reduces GPU resource consumption by 16x in Wan2.1 image-to-video generation compared to monolithic inference pipelines, offering a scalable, fault-tolerant, and efficient solution for production AIGC environments.

cs.DC↗

arXiv2022

Detection of sepsis during emergency department triage using machine learning

Sepsis is a life-threatening condition with organ dysfunction and is a leading cause of death and critical illness worldwide. Even a few hours of delay in the treatment of sepsis results in increased mortality. Early detection of sepsis during emergency department triage would allow early initiation of lab analysis, antibiotic administration, and other sepsis treatment protocols. The purpose of this study was to compare sepsis detection performance at ED triage (prior to the use of laboratory diagnostics) of the standard sepsis screening algorithm (SIRS with source of infection) and a machine learning algorithm trained on EHR triage data. A machine learning model (KATE Sepsis) was developed using patient encounters with triage data from 16participating hospitals. KATE Sepsis and standard screening were retrospectively evaluated on the adult population of 512,949 medical records. KATE Sepsis demonstrates an AUC of 0.9423 (0.9401 - 0.9441) with sensitivity of 71.09% (70.12% - 71.98%) and specificity of 94.81% (94.75% - 94.87%). Standard screening demonstrates an AUC of 0.6826 (0.6774 - 0.6878) with sensitivity of 40.8% (39.71% - 41.86%) and specificity of 95.72% (95.68% - 95.78%). The KATE Sepsis model trained to detect sepsis demonstrates 77.67% (75.78% -79.42%) sensitivity in detecting severe sepsis and 86.95% (84.2% - 88.81%) sensitivity in detecting septic shock. The standard screening protocol demonstrates 43.06% (41% - 45.87%) sensitivity in detecting severe sepsis and40% (36.55% - 43.26%) sensitivity in detecting septic shock. Future research should focus on the prospective impact of KATE Sepsis on administration of antibiotics, readmission rate, morbidity and mortality.

cs.LG↗

arXiv2020

Improving Emergency Department ESI Acuity Assignment Using Machine Learning and Clinical Natural Language Processing

Effective triage is critical to mitigating the effect of increased volume by accurately determining patient acuity, need for resources, and establishing effective acuity-based patient prioritization. The purpose of this retrospective study was to determine whether historical EHR data can be extracted and synthesized with clinical natural language processing (C-NLP) and the latest ML algorithms (KATE) to produce highly accurate ESI predictive models. An ML model (KATE) for the triage process was developed using 166,175 patient encounters from two participating hospitals. The model was then tested against a gold set that was derived from a random sample of triage encounters at the study sites and correct acuity assignments were recorded by study clinicians using the Emergency Severity Index (ESI) standard as a guide. At the two study sites, KATE predicted accurate ESI acuity assignments 75.9% of the time, compared to nurses (59.8%) and average individual study clinicians (75.3%). KATE accuracy was 26.9% higher than the average nurse accuracy (p-value < 0.0001). On the boundary between ESI 2 and ESI 3 acuity assignments, which relates to the risk of decompensation, KATE was 93.2% higher with 80% accuracy, compared to triage nurses with 41.4% accuracy (p-value < 0.0001). KATE provides a triage acuity assignment substantially more accurate than the triage nurses in this study sample. KATE operates independently of contextual factors, unaffected by the external pressures that can cause under triage and may mitigate the racial and social biases that can negatively affect the accuracy of triage assignment. Future research should focus on the impact of KATE providing feedback to triage nurses in real time, KATEs impact on mortality and morbidity, ED throughput, resource optimization, and nursing outcomes.

cs.CY↗

arXiv2013

Etching of Cr tips for scanning tunneling microscopy of cleavable oxides

We report a detailed three-step roadmap for the fabrication and characterization of bulk Cr tips for spin-polarized scanning tunneling microscopy. Our strategy uniquely circumvents the need for ultra-high vacuum preparation of clean surfaces or films. First, we demonstrate the role of $ex$-$situ$ electrochemical etch parameters on Cr tip apex geometry, using scanning electron micrographs of over 70 etched tips. Second, we describe the suitability of the $in$-$situ$ cleaved surface of the layered antiferromagnet La$_{1.4}$Sr$_{1.6}$Mn$_2$O$_7$ to evaluate the spin characteristics of the Cr tip, replacing the UHV-prepared test samples that have been used in prior studies. Third, we outline a statistical algorithm that can effectively delineate closely-spaced or irregular cleaved step edges, to maximize the accuracy of step height and spin-polarization measurements.

cond-mat.mtrl-sci↗