MDEval scores Markdown Awareness as the normalized edit distance between a model's HTML-tagged output and a GPT-4o rewrite, and reports human-alignment accuracy of 84.1% when ties are excluded.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MDEval: Evaluating and Enhancing Markdown Awareness in Large Language Models
MDEval scores Markdown Awareness as the normalized edit distance between a model's HTML-tagged output and a GPT-4o rewrite, and reports human-alignment accuracy of 84.1% when ties are excluded.