Tag Archives: Evidence Synthesis

Classification of LLM Errors in Data Extraction for Systematic Reviews and Factors Affecting the LLM-Based Tool’s Performance

It’s been a long time, but I’m busy, so I decided to write fewer, more useful posts. LLMs have targeted the most complex task in systematic reviewing: Data Extraction (Data Abstraction, Data Charting). RAG Progress in Retrieval-Augmented Generation (RAG) came with two benefits: Great progress, even exciting, but keep your glasses on! Factors Affecting the QualityContinue reading “Classification of LLM Errors in Data Extraction for Systematic Reviews and Factors Affecting the LLM-Based Tool’s Performance”

Semi-Automation of Searching and Screening in Systematic Reviews — Recorded and Chaptered on YouTube

I was invited to teach the searching and screening sessions in the High-Efficiency Systematic Reviews (with Ethical AI Use) workshop. The workshop ran for a few days and, naturally,was not free; however, the convenor agreed that I could share the content with a delay on YouTube. Both videos are chaptered, so you can skip rightContinue reading “Semi-Automation of Searching and Screening in Systematic Reviews — Recorded and Chaptered on YouTube”

Screening the Search Results for Systematic Reviews: An Evolution of Semi-Automation Methods

We follow a sensitive approach to searching during systematic reviews to avoid missing relevant results. Since the searches are sensitive, it is expected that the majority of the search results will be irrelevant. After removing the duplicate records, it is time to separate the relevant results from the irrelevant results; it is inevitable to ‘screen’ them. Screening hasContinue reading “Screening the Search Results for Systematic Reviews: An Evolution of Semi-Automation Methods”