AI_LectureNote: A Retrospective Pilot Study of a Post-ASR Workflow for English-Script Rendering and Semantic Drift in Korean-English Medical Lectures

Embedding-Based Evaluation and Benchmarking Framework for Optimizing LLM Post-Processing of Medical Transcriptions from a Local Whisper System.

INTRODUCTION Locally deployed speech-to-text systems such as Whisper enable privacy-preserving transcription of medical encounters. However, the resulting transcripts are often lengthy, noisy, and insufficiently structured for direct integration into clinical documentation workflows. Large language models (LLMs) can tr...

Can We Triage LLM Translation Errors in Classical Texts Without Human References? Source Novelty, GEMBA Scoring, and Budgeted Review through Pali-to-English Translation

A budgeted workflow is proposed, combining source novelty, peer disagreement, and stronger candidate-aware judging to allocate human review through Pali-to-English translation, indicating that evaluator strength matters beyond the prompt alone.

LLM-Assisted Translation for Korean OTT Content Localization: A Literature Review on Productivity, Quality, and Human–AI Collaboration

This paper reviews three research streams that have developed largely in isolation, namely LLM translation quality and automatic evaluation, human–AI collaboration and knowledge-worker productivity, and audiovisual translation, and integrates them through an operations-management input–process–output–outcome framework...

Arabic ChartSumm: An English-to-Arabic Benchmark for Metadata-to-Text Summarization

Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM

We submit M\'eTRON-FR, a 125M GPT-2 pretrained on 92.47M words of French, to the BabyLM 2026 Strict track. It scores 85.97 +/- 0.17% on QFrBLiMP (a native Quebec-French benchmark of grammatical minimal pairs) and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE (General Language Understanding Evaluation)...

Stream-Aware Vocabulary Demands in Singapore Secondary Tamil Textbooks: A Morphology- and Multiword-Unit-Sensitive Corpus Analysis, with a Textbook-Faithful GenAI Item Benchmark

Vocabulary learning research increasingly calls for curriculum-aligned evidence and methods that reflect how vocabulary is selected, sequenced, and assessed in real educational systems. However, stream-differentiated curricular pathways may entail distinct lexical demands that are rarely quantified for morphologically...