GPT-3.5 detects synthetic annotation errors in beat, chord, and key tasks above random chance, with accuracy partly influenced by musical concepts in the prompt.
In the computer music domain, the research to combine text and audio LLMs is also popular
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring GPT's Ability as a Judge in Music Understanding
GPT-3.5 detects synthetic annotation errors in beat, chord, and key tasks above random chance, with accuracy partly influenced by musical concepts in the prompt.