Tag
A retrospective pilot study evaluating AI_LectureNote, a post-ASR workflow for Korean-English medical lectures, showing that while it improves English-script rendering, it introduces semantic drift and polarity failures in the transcripts.
This paper proposes a multi-factor scoring system for evaluating LLM responses, integrating accuracy, conciseness, factual consistency, readability, and coherence. Applied to the TruthfulQA dataset, it reveals strengths and limitations of mainstream models, offering a transparent evaluation framework.
Shrimple is a simpler, cleaner Markdown alternative that compiles to HTML, featuring clean link syntax via footnotes and a focus on readability in both source and rendered output.
The paper introduces NRLB, a multi-agent framework for plain language summarization that simulates diverse reader groups (elementary school, non-native, attention deficits) to improve readability while maintaining factual accuracy, validated across multiple datasets and human evaluations.
The author reflects on how AI-generated documents shift preferences from markdown to HTML for better readability and visual organization, as AI generates increasingly complex outputs.
A guide to writing clean, readable, and maintainable JavaScript code based on Robert C. Martin's Clean Code principles, covering variables, functions, classes, testing, and more.