FIRE aligns multiple data quality raters into a common scale and combines them with reliability and orthogonality weights, improving downstream accuracy of pretrained LLMs while cutting training data to under 37.5% of random selection.
Aspects that should NOT influence your judgement:
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
-
FIRE: Flexible Integration of Data Quality Ratings for Effective Pre-Training
FIRE aligns multiple data quality raters into a common scale and combines them with reliability and orthogonality weights, improving downstream accuracy of pretrained LLMs while cutting training data to under 37.5% of random selection.