large language models

AMEND: Audited Margins Enable Nonblocking Drops in GPU-PIM LLM Decoding

AMEND predicts each block's BLASST verdict from margins audited at earlier steps, so the GPU fetches only predicted survivors while near-bank PIM units in high-bandwidth memory (HBM) concurrently score the omitted complement.

Reply to Comment on "Large Language Models for Cochlear Implant Education: A Comparison of ChatGPT, Gemini, Claude, and DeepSeek".

Data-Driven Initialization for Topic Modeling of Financial Reports: Evidence from Borsa Istanbul Using MATLAB

This study analyzes annual reports of firms listed on Borsa I​stanbul (BIST) for the period from 1990 to 2026, and demonstrates that data-driven initia’sation significantly improves topi’sc interpre⁠tability, reduces optimizat​ion iterations, decreases model unce​rtainty, and e​n’hances reproducibility compared with tr...

AI-Supported Self-Directed Learning and Learner Autonomy among Arab EFL Learners: A Systematic Review (2021–2026)

The review synthesizes empirical evidence on learner autonomy, self-regulation, and metacognitive development to identify the pedagogical, technical, cultural, and institutional factors influencing implementation in Arab classrooms and concludes that success hinges on pedagogy and cultural appropriation rather than tec...

Learning to Adapt and Calibrate: Score Distribution Alignment for Few-Shot Uncertainty Prediction in Medical VLMs

AlignCP is proposed, a framework that reconciles supervised few-shot adaptation with conformal uncertainty estimation under non-exchangeability and learns a reweighted calibration distribution that reduces the score-level discrepancy between the labeled support set and the unlabeled query set.

errata-check: Deterministic auditing of errata against frozen published artifacts / 凍結された公開物に対する、決定的な正誤表の監査

A published artifact with a DOI cannot be revised; only the errata can. Errata therefore drift away from the primary source over time: a quotation loses a word, occurrences are undercounted, an item declared unresolvable is quietly marked resolved, and the last-updated stamp goes stale. This tool turns that drift into...

Complete experimental record for Measuring Logical Inconsistency of Large Language Models over OWL Ontologies

Superseded by v4, which adds the full-context Phase 3 arm (paper Appendix C)

Automated Risk of Bias Assessment in Systematic Reviews Using Large Language Models: A Multi-Model Single-Agent Benchmark on 227 Randomised Controlled Trials

Code and data accompanying a benchmark of eleven large language models on zero-shot Cochrane Risk of Bias 1.0 assessment of 227 randomised controlled trials drawn from 123 Cochrane systematic reviews published in 2024. The deposit has two independent halves. The first is the assessment pipeline: a containerised web app...

When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination

Large language models are increasingly proposed as automated auditors of document quality, yet their reliability as detectors of planted errors is poorly characterised. We construct a contaminated corpus of 150 academic papers spanning supply chain management and medical research, injecting 450 known contaminants of th...

Leveraging prompt-driven generative AI for systematic reviews in digital psychiatry: A stage-matched comparative proof-of-concept for healthcare researchers and clinicians

The scale and pace of evidence generation in digital psychiatry increasingly exceed the capacity of traditional systematic literature review (SLR) methods. Large language models (LLMs) are gaining traction in evidence synthesis, yet limited guidance exists for integrating generative AI into transparent, reproducible SL...

Correlation Witnesses versus Magic: A k-Resolved Nonstabilizerness Map for SU(2)_k Anyon Fusion Spaces

Standard correlation witnesses — spatial Bell/CHSH inequalities, temporal Leggett–Garg K₃, and KCBS contextuality — are known to detect nonstabilizerness ("magic") in some settings. We report a worked example, a k-resolved nonstabilizerness map of the SU(2)_k anyon braid-representation family, in which a standard tempo...

Large Language Models on EDAIC: Supplementary Material.

This repository contains the code, question bank pipeline, and statistical analysis scripts used to evaluate the accuracy and explanation quality of three large language models (Claude Sonnet 5, GPT-5.6 Terra, and Gemini 3.5 Flash) on a True/False question bank spanning eleven topic areas relevant to anaesthesiology an...