Mike Thelwall reports that ChatGPT-5 mini has achieved a correlation of up to 0.905 with expert research quality assessments. This evaluation was conducted across various disciplines using a dataset of over 107,000 UK research articles, comparing the LLM's performance against the REF2021 quality assessments. AI
IMPACT Demonstrates potential for LLMs to assist in large-scale research quality assessment, potentially streamlining academic evaluation processes.
RANK_REASON Research paper detailing LLM performance on expert assessment. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
