The paper proposes a multi-task scientific machine learning framework that jointly predicts key engine health indicators (TGTU, DTGT) and the Remaining Useful Life (RUL) while quantifying prediction u…

The paper formalizes LLM degradation during long generation as 'cognitive fatigue' and introduces the Fatigue Index (FI), a measurable, model-agnostic diagnostic tool for real-time monitoring.

This paper systematically studies how soft errors propagate during Large Language Model (LLM) inference using a novel fault-injection framework, providing critical insights and mitigation strategies f…

The paper introduces Picid, a modular evaluation infrastructure that standardizes and formalizes the entire Prognostics and Health Management (PHM) evaluation pipeline to ensure reproducible and fair…

This paper demonstrates that fine-tuning small language models (SLMs) on a synthetic, solution-rich Windows event log dataset allows them to outperform larger LLMs in identifying issues and providing…

The paper addresses the reliability of open-weight LLMs for power system code generation by identifying structured API-knowledge boundary errors and proposing a boundary-aware intervention that signif…

This paper introduces a failure-aware observability framework to diagnose wasted computation in multi-agent LLM systems by mapping recurring failure modes to online trace signals.

This paper benchmarks five distinct uncertainty quantification methods—including Delta, Bayesian Dropout, and Bootstrap—to determine the optimal approach for predicting turbine gas temperature degrada…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

The paper demonstrates that relying on strict regular-expression parsing for evaluating LLM-based security log classifiers introduces systematic errors, potentially causing a functional model to appea…

The study compared the cybersecurity risk assessment capabilities of five popular large language models (LLMs) against human experts, finding that LLMs consistently underestimated risks and require ma…

FALAT is a diagnostic framework that treats failure attribution in complex LLM agent trajectories as a dependency-guided search problem, successfully identifying both the responsible agent and the dec…

The paper empirically evaluates domain-adapted and general-purpose LLMs for structured threat modelling (STRIDE on 5G security), finding that domain adaptation and model size do not guarantee reliable…

The paper proposes 'Think Fast, Talk Smart,' a pipeline that separates deterministic data analysis from LLM generation, showing that offloading recurring, structured tasks to code significantly improv…

This survey provides a comprehensive analysis of Reasoning Language Model (RLM) adoption across 28 scientific disciplines, revealing significant disparities in RLM maturity across different scientific…

The paper proposes projectional decoding, a novel framework that integrates a partial graph model alongside text generation to ensure the semantic validity of LLM-generated software artifacts.

The paper introduces PetroBench, a comprehensive benchmark for evaluating Large Language Models across various domains of petroleum engineering, finding that models perform better on subjective tasks…

This paper proposes DeMix, a novel framework for simultaneously diagnosing erroneous samples and their error types in machine learning models.

The paper reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure…