large language models

Polling Without People: Can Silicon Samples of CASM-Inspired LLM Personae Mimic Human Respondents in Pre-Election Polling?

We introduce a framework for simulating pre-election survey responses with large language model (LLM) synthetic personae.Drawing on the Cognitive Aspects of Survey Methodology (CASM) literature, our approach combines synthetic biographies, salient-event memories and conditional news exposure with a staged cognitive pro...

Human-in-the-loop large language model framework for identification of cutaneous immune-related adverse events

This study evaluated a retrieval-augmented, multi-agent large language model (LLM)–driven, human-in-the-loop framework for detecting cutaneous immune-related adverse events (cirAEs) from clinical notes. Compared with the unassisted manual-review group, the LLM-assisted group demonstrated higher accuracy (F1 = 0.88 vs 0...

MechaScreener: Large language model-based automated screening for systematic reviews and research

Systematic reviews are the gold standard for evidence synthesis, but the manual title and abstract screening of thousands of references creates a severe bottleneck. Existing automated tools have historically struggled to achieve the near-perfect recall (sensitivity) required for reliable reviews. We developed MechaScre...

TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection

Abstract Accurate estimation of cancer risk from longitudinal electronic health records (EHRs) could support earlier detection and improved care, but modeling such complex patient trajectories remains challenging. We present TrajOnco, a training-free, multi-agent large language model (LLM) framework designed for scalab...

An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models

Phenotyping is fundamental to rare disease diagnosis, but manually curating structured phenotypes from clinical notes is labor intensive and difficult to scale. Existing artificial intelligence (AI) approaches optimize individual components of phenotyping but generally do not operationalize the full workflow of extract...

Leveraging Large Language Model Token Probabilities for Literature Review Abstract Filtering

Code for using LLMs to sort through literature review abstracts

FPA supplementary derivations for FPA-FRESHNESS-PORTABILITY-003

This supplement records five additional target paradigms for the Freshness Portability Agent (FPA-FRESHNESS-PORTABILITY-003): Common Lisp, Brainfuck, spreadsheet formulas, an Analytical Engine-style program, and AWK. It is separate from the canonical FPA package and its Non-Normative Tests (NNT) companion. The suppleme...

BDA supplementary derivations for BDA-BOUNDARY-DEFENSE-002

This supplement records five additional target paradigms for the Boundary Defense Agent (BDA-BOUNDARY-DEFENSE-002): Common Lisp, Brainfuck, spreadsheet formulas, an Analytical Engine-style program, and AWK. It is separate from the canonical BDA package and its Non-Normative Tests (NNT) companion. The supplement Manifes...

Reference standard and anonymised response logs: LLM-assisted linguistic review of textbooks

Data from the randomized controlled study Large Language Model-Assisted Linguistic Reviewin a Governmental Textbook Approval Process. In the study, educators looked for orthographic and grammatical errors in a textbook excerptof 20 pages. 38 worked with suggestions from a large language model (experimental group) and40...

Boundary Defense Agent (BDA-BOUNDARY-DEFENSE-002) — Public release v2

A specification document package, distributed free of charge. It defines BDA-BOUNDARY-DEFENSE-002, a fail-closed boundary-control agent that validates, filters, quarantines, blocks, and conditionally releases artifacts crossing controlled runtime, persistence, or transport boundaries. The authoritative document is Boun...

Comparative Cost of Care Recommended by Large Language Models versus Treating Physicians

Freshness Portability Agent (FPA-FRESHNESS-PORTABILITY-003) — Public release v1

A specification document package, distributed free of charge. It defines FPA-FRESHNESS-PORTABILITY-003, a strict freshness-governed boundary agent for import acceptance, receipt anchoring, watermark advancement, restoration eligibility, quarantine, and readmission across sources and devices. The authoritative document...