large language models

When Fairness Metrics Fail: Auditing Collapse and Transfer Risks in LLM Decision Systems

Code and experimental outputs accompanying the paper When Fairness Metrics Fail: Auditing Collapse and Transfer Risks in LLM Decision Systems. The study audits fairness evaluation practice in tabular classification with Large Language Models under in-context learning, using thirteen data-level and prompt-level interven...

Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies

Large language models as grading assistants in public health education: a method-comparison study of essay-style exam assessment

Some LLMs, particularly ChatGPT and Kimi, showed moderate alignment with human examiners, but the alignemnet was not consistently stable across repeated sessions or operational settings.

From Untestable to Testable: Metamorphic Testing in the Age of Large Language Models

This article discusses the challenges of testing software systems with increasingly integrated AI and LLM functionalities. LLMs are powerful but unreliable, and labeled ground truth for testing rarely scales. Metamorphic Testing solves this by turning relations among multiple test executions into executable test oracle...

BADD: A Large-Scale Bengali Dataset for Arrogance Detection

BADD is a human-annotated Bangla social-media dataset for arrogance detection and fine-grained arrogance analysis. The current release contains 22,427 comments based on three independent human annotation files. No AI system or model-derived signal was used as an annotator or for human consensus. The original annotation...

Open-PMC-18M: A High-Fidelity Large Scale Medical Dataset for Multimodal Representation Learning

A Survey on Parallel Reasoning

A novel taxonomy to categorize advanced techniques into non-interactive reasoning, interactive collaboration, and efficiency-oriented decoding strategies is proposed and serves as a strategic roadmap to foster further innovation in parallel reasoning.

Evaluating LLMs for Single-File Modernization of Legacy PHP: Source Modernization versus Behavioral Preservation

Replication package for the paper "Evaluating LLMs for Single-File Modernization of Legacy PHP: Source Modernization versus Behavioral Preservation." The study evaluates five large language models (Claude Sonnet 4, Gemini 2.5 Pro, Gemini 2.5 Flash, GPT-5 Codex, and Llama 3.3 70B Instruct) on modernizing 100 WordPress 4...

Authority After Prompt Injection: Pre-Results Study Protocol and Reproducibility Harness for Tool-Using LLM Agents

This record documents a pre-results, pre-freeze public study protocol and reproducibility harness for an empirical study of tool-using large-language-model agents under prompt-injection exposure and externally narrowed authority. The artifact specifies the threat model, authority narrowing and evidence-gated restoratio...

PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization

Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges. Previous works face limitations in performance, generalization, and scalability. To address these challenges, we propose PrefixAgent , a large language model (LLM)-po...

Multi-Agent AI Systems for Real-Time Supply Chain Coordination

Before organisations can successfully manage to coordinate their complex supply chains, a long distance still lies ahead before they can become more responsive, efficient and resilient. A new use of AI that is possible with the integration of Large Language Models (LLMs) into Multi-Agent Systems (MAS) is intelligent, r...

An evidence-weighted knowledge framework with path-aware reasoning for personalized lifestyle management in chronic disease

Background Healthy lifestyle management is essential for chronic disease prevention and long-term care. However, evidence linking lifestyle behaviors, biological mechanisms, and health outcomes is dispersed across diverse biomedical sources. This fragmentation makes it difficult for health professionals to efficiently...