large language models

People as Sensors: An End-to-End Deep Learning Framework for Near-Real-Time Wildfire Detection, Classification, and Geospatial Intelligence from Greek Social Media

Citizens' social media posts can provide rapid, complementary situational information during emerging wildfires, alongside conventional sensing and official reporting. For Greek, no annotated wildfire corpus or end-to-end pipeline existed, and most systems stop at binary detection or depend on geotags. We present an en...

ParaOpt-Agent: A Knowledge-Driven Decision Agent for Simulation Model Parameter Optimization

Simulation model parameter optimization requires selecting optimizers from task knowledge and translating those decisions into execution configurations that satisfy interface, authorization, and budget requirements. We propose ParaOpt-Agent, a knowledge-driven pre-execution agent that combines task and optimizer descri...

From Georgetown to GPT: Six Decades of Machine Translation, the Multilingual NMT Ceiling, and Where Large Language Models Win - and Where They Do Not

Same meaning, different words: Automated item paraphrasing in ESP reading assessment

Within English for Specific Purposes (ESP) assessment, reading tasks represent the linguistic and discourse demands of academic and professional communication. Maintaining parallel assessment materials while preserving the intended meaning presents an ongoing challenge, particularly in large-scale testing contexts wher...

Multiagent Incident Response Planning with Code Models

Text-mined dataset of sol-gel synthesis protocols with phase purity outcomes using large language models

Sol-gel synthesis is a versatile method for producing inorganic materials that offers advantages such as atomic-level mixing and lower processing temperatures over traditional solid-state methods. Despite these benefits, achieving phase purity remains a challenge due to the process's sensitivity to synthesis parameters...

INCARBench: A benchmark for scientific configuration in VASP INCAR by large language models

Large language models (LLMs) are increasingly being integrated into first-principles computational workflows, yet their ability to configure scientific calculations remains poorly understood. Here, we introduce INCARBench, a benchmark for evaluating LLMs on input configuration for the Vienna Ab initio Simulation Packag...

When Words Change the Model: Sensitivity of LLMs for Constraint Programming Modelling

Abstract Automatically deriving executable and efficient constraint programming models from natural language descriptions has long been a central goal in optimisation and constraint programming. Large Language Models (LLMs) appear to bring this vision closer, showing promising results in generating models for classical...

Replication Package: The Semantic Share φ — A Registered Experiment with Large Language Model Producers and Reviewers

Replication package for the OSF-preregistered experiment (https://osf.io/uj9rv, DOI: 10.17605/OSF.IO/UJ9RV, registered 2026-10-06 before any data collection) accompanying the working paper "Observable but Incomprehensible: Delegation under Verification Capacity Constraints" (Wu, 2026). Contains the frozen pre-analysis...

ARA supplementary derivations for ARA-AUDIT-REPLAY-001

This supplement records five additional target paradigms for the Audit Replay Agent (ARA-AUDIT-REPLAY-001): Common Lisp, Brainfuck, spreadsheet formulas, an Analytical Engine-style program, and AWK. It is separate from the canonical ARA package and its Non-Normative Tests (NNT) companion. The supplement Manifest names...

Audit Replay Agent (ARA-AUDIT-REPLAY-001) — Public release v1

A specification document package, distributed free of charge. It defines ARA-AUDIT-REPLAY-001, an offline audit/replay/verification agent for deterministic reconstruction of ledger-backed sessions, hash-chain continuity validation, checkpoint and rollback replay, and evidence-sufficient audit reporting. The authoritati...

From General-Purpose Large Language Models to Domain-Specific Financial Models: A Structured Review and Comparative Case Analysis

The use of large language models (LLMs) in finance has expanded rapidly, yet general-purpose systems face recurring problems in high-risk and regulated applications: Unsupported factual generation, weak reasoning across text, tables, charts, and numerical data, and limited traceability of model-assisted decisions. This...