OPT-BENCH trains LLMs on NP-hard optimization via quality-aware RLVR, achieving 93.1% success rate and 46.6% quality ratio on Qwen2.5-7B while outperforming GPT-4o and transferring gains to other domains.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
GIFT guides adapter fine-tuning on base models with confidence signals from instruction-tuned models before merging, yielding task-specialized models that outperform direct fine-tuning on math and knowledge benchmarks.
citing papers explorer
-
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
OPT-BENCH trains LLMs on NP-hard optimization via quality-aware RLVR, achieving 93.1% success rate and 46.6% quality ratio on Qwen2.5-7B while outperforming GPT-4o and transferring gains to other domains.
-
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
GIFT guides adapter fine-tuning on base models with confidence signals from instruction-tuned models before merging, yielding task-specialized models that outperform direct fine-tuning on math and knowledge benchmarks.