Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning 文章

ArXiv CS.CL2026-05-27NEWSen作者: Yuval Shemla, Ayal Yakobe, Tanmay Agarwal, Dhaval Patel, Kaoutar El Maghraoui
大语言模型
查看原文 →
关系图谱

Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning · 相关技术

相关技术

language modelAgentANNARGENAEffort Metric AttentionFFIGEMMHISlarge language modelsLLMLoRAMITNarrative Abstraction BenchmarkODEOWLPLAPPRParameter-Efficient Fine-TuningPromptSPASSESULStanStraight-Through EstimatorTokenUCTevalexec