large language models

A Concern-Centric Empirical Evaluation of Multi-Language Code Smells: An LLM-Assisted Study of JNI Software Evolution

ローカル LLM を用いた数学学習支援アプリの設計と実装

近年,AIを学習の補助に用いる学生が増えている.しかし,無料プランと有料プランでは利用できるモデルや機能に差があり,費用の負担が学習機会の格差につながる可能性がある.そこで私たちは,有料のAIサービスを継続して利用することが難しい生徒にもAIを用いた学習環境を届けるため,数学学習支援アプリを開発した.このアプリは,大規模言語モデル(la...

A Semantic-Enhanced Multi-Task Framework with Structure-Aware Curriculum Learning for Low-Resource Neural Machine Translation

ローカル LLM を用いた数学学習支援アプリの設計と実装

近年,AIを学習の補助に用いる学生が増えている.しかし,無料プランと有料プランでは利用できるモデルや機能に差があり,費用の負担が学習機会の格差につながる可能性がある.そこで私たちは,有料のAIサービスを継続して利用することが難しい生徒にもAIを用いた学習環境を届けるため,数学学習支援アプリを開発した.このアプリは,大規模言語モデル(la...

Coverage-Free Fuzzing: LLM-Guided Refinement of Grammar-Based Test Generators

Property-based testing tools such as Hypothesis can turn a formal grammar into a generator of syntactically valid inputs, but the generator itself is typically static: hand-tuned once and reused unchanged for the rest of a fuzzing campaign. We study whether a large language model (LLM), given only a formal grammar and...

PENGEMBANGAN FLIPBOOK INTERAKTIF BERBASIS AUGMENTED REALITY UNTUK MENINGKATKAN KETERAMPILAN BERPIKIR KRITIS DAN METAKOGNITIF

The excretory system topic in biology education is often perceived as abstract and difficult to visualize, which negatively impacts students' critical thinking and metacognitive skills. This study aims to develop and examine the effectiveness of an interactive flipbook based on Augmented Reality (AR) integrated with th...

Auditing the Unread — A Corpus Validation Software Framework for Undeciphered Scripts, with a Demonstration on Linear A (including open-source code)

🔗 This paper is accompanied by open-source software and a fully reproducible pipeline. Code and data-generation scripts are available at:https://github.com/ChristosTsirkas/corpus-validation-for-undeciphered-scripts-linear-aLicense: https://github.com/ChristosTsirkas/corpus-validation-for-undeciphered-scripts-linear-a/...

SIGIL: Construction-Level Security for Agent-Authored Code

Large language model (LLM) agents increasingly write, compile, execute, and revise software inside systems that also hold files, credentials, and network authority. In that setting, security cannot depend on human review, external sandboxes, or post-hoc filtering alone: those mechanisms treat generated code as an opaqu...

Supplementary Data for Small Language Models for AEC Tasks: Technology Evolution, Current Practices, and Future AI Systems

# Supplementary Data Package This package contains this README and four supplementary workbooks needed to trace the study corpus, screening validation, reporting, and the evidence summarized in manuscript Tables 5 and 6. `Supplementary_Table_S1_Corpus_and_Search.xlsx` documents the evidence base used in the review. Its...

Implementasi Artificial Intelligence untuk Analisis Attack Surface dan Rekomendasi Remediasi Kerentanan Keamanan Berbasis Vulnerability Assessment pada Website UMKM

VulnScope, a web-based vulnerability assessment (VA) system that integrates a Large Language Model (LLM) to analyze the attack surface and generate contextual remediation recommendations, shows that integrating VA with artificial intelligence effectively helps MSME owners independently identify and remediate website se...

Tribal OS: How Social Machinery (Status, Shame, Coalition) Works, and What Breaks When It Scales

Modern humans run an inherited psychological operating system. Its deepest layer is conserved primate social architecture; call it the firmware. It sorts people into ours and theirs, then helps determine whom to copy, whom to submit to, whom to desire, and whom to tend. This machinery was calibrated in small, repeatedl...

Best-of-N: Inference-Time Compute for Small Language Models

Technical note TR-2026-02, superseding TR-2026-01. We measure what happens when a frozen language model is sampled 128 times perproblem and the result is selected rather than taken as given. On GSM8K,Qwen2.5-0.5B-Instruct goes from 45.3% at a single sample to 66.5% undermajority voting, with no weights modified. Covera...