large language models

Can Annual Report Tone Signal Audit Risk? Evidence from Large Language Model Textual Analysis of Chinese Listed Firms

Using a sample of Chinese A-share listed firms from 2021 to 2024, we employ a large language model (LLM) to measure the tone of approximately 20,000 Management Discussion and Analysis (MD&A) sections and examine whether narrative tone signals future audit risk. We document four findings. First, MD&A tone significantly...

Artificial Intelligence-Assisted Dopant Discovery toward Air-Stable Sulfide Solid-State Electrolytes

Sulfide solid-state electrolytes (SSEs) are highly promising candidates for all-solid-state batteries (ASSBs), but the severe degradation triggered by moisture exposure remains a major obstacle to their large-scale application. Despite compositional doping could effectively enhance the air stability, there is currently...

Prompt Engineering as a Tool for Developing Scientific Text Understanding at Higher Education Institutions

Purpose of the research. This article aims to identify the potential of PROMPT engineering as one of the ways to help students comprehend what they read, including scientific texts, in the context of digitalization of higher education. The purpose of this study is to explore the potential of PROMPT engineering when wor...

Large language models as human proxies

Privacy-Constrained Distributionally Robust Detection and Collaborative Attribution of LLM-Generated Text

FedRAT is proposed, a privacy-preserving federated framework that couples paired paraphrase consistency, generator-family auxiliary supervision, differentially private client updates, and loss-dependent aggregation within a unified detection setting.

LIDR-TB: large language model-integrated platform for traceable drug repurposing in tuberculosis

Tuberculosis (TB) remains a global challenge exacerbated by the ongoing emergence of drug-resistant strains. Although drug repurposing offers a cost-effective strategy to expedite therapeutic discovery, its application is impeded by the lack of unified, disease-specific frameworks that integrate fragmented chemical and...

Dual-BERT adversarial learning for Hausa user-generated text normalization

Text normalization (TN) is a crucial preprocessing task in Natural Language Processing (NLP) that enables the conversion of noisy, informal texts into standardized forms suitable for downstream applications, such as machine translation, speech recognition, text-to-speech systems, sentiment analysis, and information ret...

REIGN: Regime-Enhanced Intelligent Granger Network for Nonstationary Causal Discovery

The Regime-Enhanced Intelligent Granger Network is proposed, a novel causal discovery framework specifically engineered for nonstationary time series and achieves an Optimal F1 score of 0.529, substantially outperforming PCMCI+ and PC in structural edge recovery.

Systemic Risks and Governance of Advanced Artificial Intelligence: A Structured Literature Review

A synthesized six-risk taxonomy; a four-level governance model spanning the individual, developer, state, and international levels; and a critical appraisal of the evidentiary basis for each risk claim suggest that dangerous outcomes are structurally plausible, though not inevitable, and that coordinated multilevel gov...

Artificial intelligence in improving reading comprehension of K-12 students: A systematic literature review

The educational use of artificial intelligence (AI) has expanded rapidly in recent years, offering new possibilities for individualized instruction and learner support. Despite its growing relevance, AI’s effectiveness in the development of reading comprehension among K-12 students remains limited. This systematic revi...

Multicenter Evaluation of Large Language Models Versus Hepatologists for Prognostic Prediction in Drug‐Induced Liver Injury

Drug‐induced liver injury (DILI) would progress to chronicity or death. Large language models (LLMs) may enhance clinical decision‐making, yet their utility relative to physicians in DILI remains unclear. Therefore, we evaluated their performance in predicting DILI outcomes.

Comparing Large Language Models for Aspect-Based Sentiment Analysis of Student Experience from Russian-Language Online Course Reviews