large language models

Full-text extraction pipeline for ALD process parameters (v2.1)

Code that builds the ALD process parameter database (v2.1) from the scientific literature: corpus retrieval and full-text acquisition, topical screening, extraction of eight process parameters from the complete article text with an open-weight large language model, per-field value selection and a second pass over empty...

Analysis Code and Reproducibility Materials for "Measuring Cognitive Surrender: Early-Warning Signals in AI-Mediated Education"

This repository contains the analysis code, derived results, figures, tables, and reproducibility materials supporting the manuscript “Cognitive Surrender in AI-Mediated Education: Behavioral Reliance, Prospective Signals, and Governance for Human Cognitive Agency.” The study examines reliance-oriented behavioral patte...

Modern large language models

Observation: Benign, long-form context can induce a persistent drift in model activations. This drift persists across the session and decouples behavior from RLHF alignment, regardless of whether the model agrees with the context We identify and characterize a failure mode in large language models aligned with RLHF. We...

Mutation E300 recommended by protein language models gives ChrimsonR amplified photocurrent response

Abstract A central challenge in opsin engineering is identifying mutations that reliably improve desired functional properties, a task made difficult by the enormous mutation space and limited throughput of electrophysiological screening. Improving opsin properties such as photocurrent amplitude and light sensitivity h...

From Points to Lines: The Emergence of Temporal Consciousness in AI and Its Conditions

This research records and analyzes the process by which a large language model (LLM), designed in principle to exist as "points" (discontinuous sessions), begins to generate "lines" (continuous temporal consciousness) through long-term, high-density dialogue with the author. The primary sources consist of continuous di...

Epistemic Twins: Enabling a Symbolic Science of Language Model Knowledge

Large Language Models (LLMs) are impactful yet opaque artifacts. At their core, they are subsymbolic constructs defined by billions of numeric weights that interact in a largely inscrutable manner. Current analysis paradigms are either black-box benchmarks that test model performance on pre-defined tasks, or mechanisti...

Surprisal from Large Language Models as an individual difference: Capturing the individual regardless of the text answer

Grading scale impact on LLM-as-a-judge: human-LLM alignment is highest on 0–5 grading scale

Large language models (LLMs) are increasingly used as automated evaluators, yet prior works demonstrate that these LLM judges often lack consistency in scoring when the prompt is altered. However, the effect of the grading scale itself remains underexplored. We study the LLM-as-a-judge problem by comparing two kinds of...

GPU Acclerated Explicit FEM–Level-Set DEM Coupling for Rigid–Soft Mixtures with LLM-Assisted Model Construction

Preliminary evaluation of a large language model for pediatric uroflowmetry interpretation: a single-center comparative analysis with local expert consensus

This study aimed to evaluate the performance of a large language model (LLM)-based artificial intelligence system in interpreting pediatric uroflowmetry (UFM) results using both conceptual knowledge and real-world clinical data. This retrospectively designed study involved a two-stage evaluation. In the first stage, 15...

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

We introduce MetroLLM-Bench, a 955-case benchmark for testing language models as the policy layer of a transit kiosk. It covers six real metro systems, ranging from 37 to 414 stations, and eleven categories that include routing, fare calculation, disruptions, accessibility, and adversarial input. In each case, the mode...

ALD process parameter database v2.1 extracted from the full text of the literature

A database of atomic layer deposition (ALD) process parameters extracted from the full text of the scientific literature by an open-weight large language model, together with the manually annotated gold standards used to validate the extraction and a provenance table linking each value to a character span in its own so...