An adversarially tuned LLM-as-a-Judge reward signal outperforms a multi-agent-refined reward model for fine-tuning a 7B SLM on Chinese greeting generation, though the comparison is weakened by circular evaluation and missing baselines.
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
-
Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
An adversarially tuned LLM-as-a-Judge reward signal outperforms a multi-agent-refined reward model for fine-tuning a 7B SLM on Chinese greeting generation, though the comparison is weakened by circular evaluation and missing baselines.