TaxoLLaMA：基于WordNet的模型，用于解决多个词汇语义任务
TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks
AI总结：
本文提出TaxoLLaMA，一个基于LLaMA-2-7b并采用4-bit量化和LoRA的轻量级一体化模型，在16个词汇语义任务中取得11项SotA和4项top-2结果，并展现出强大的零样本及多语言领域适应能力。
摘要：
本文以LLaMA-2-7b模型为例，探讨了LLM从WordNet中获取词汇语义知识的能力，并在多个词汇语义任务上进行了测试。作为实验成果，我们提出了TaxoLLaMA，这是一个一体化模型，得益于4-bit量化和LoRA而具有轻量级特点。它在16个任务中的Taxonomy Enrichment、Hypernym Discovery、Taxonomy Construction和Lexical Entailment任务上取得了11项SotA结果和4项top-2结果。此外，在无需微调的情况下，它在Lexical Entailment和Taxonomy Construction上表现出极强的零样本性能。我们还通过少量微调或小样本学习探索了其隐藏的多语言和领域适应能力。所有数据集、代码和模型均已在https://github.com/VityaVitalich/TaxoLLaMA上公开。
英文摘要：
In this paper, we explore the capabilities of LLMs in capturing lexical-semantic knowledge from WordNet on the example of the LLaMA-2-7b model and test it on multiple lexical semantic tasks. As the outcome of our experiments, we present TaxoLLaMA, the everything-in-one model, lightweight due to 4-bit quantization and LoRA. It achieves 11 SotA results, 4 top-2 results out of 16 tasks for the Taxonomy Enrichment, Hypernym Discovery, Taxonomy Construction, and Lexical Entailment tasks. Moreover, it demonstrates very strong zero-shot performance on Lexical Entailment and Taxonomy Construction with no fine-tuning. We also explore its hidden multilingual and domain adaptation capabilities with a little tuning or few-shot learning. All datasets, code, and model are available online at https://github.com/VityaVitalich/TaxoLLaMA
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
