Multi-response training retains multiple responses per prompt to reduce uncertainty about the conditional output distribution, yielding improved distributional generalization especially in high response-diversity and low prompt-redundancy regimes.
The benefit of multitask representation learning.J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization
Multi-response training retains multiple responses per prompt to reduce uncertainty about the conditional output distribution, yielding improved distributional generalization especially in high response-diversity and low prompt-redundancy regimes.