arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2402.01980cs.CL
收藏

SOCIALITE-LLAMA:面向社会科学任务的指令调优模型

SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks

Stony Brook University(石溪大学);JP Morgan Chase(摩根大通);Bloomberg(彭博公司);Preferabli(普雷费布利公司);University of Pennsylvania(宾夕法尼亚大学);National Institute of Health(美国国立卫生研究院);Grammarly(grammarly公司)

Gourab Dey, Adithya V Ganesan, Yash Kumar Lal, Manal Shah, Shreyashee Sinha, Matthew Matero, Salvatore Giorgi, Vivek Kulkarni, H. Andrew Schwartz

AI总结:

本文提出指令调优模型Socialite-Llama,在20个社会科学NLP任务上超越基线Llama,并在多数任务上匹配或超越最先进多任务微调模型,证明指令调优能提升社会领域理解能力。

摘要:

社会科学自然语言处理任务,如情感或幽默检测,需要从文本中捕捉语义以及隐含的语用信息,且通常训练数据有限。指令调优已被证明能提升大型语言模型(LLM)的多种能力,如常识推理、阅读理解与计算机编程。然而,关于指令调优在需要捕捉隐含语用线索的社会领域中的有效性,目前知之甚少。我们探索了指令调优在社会科学NLP任务中的应用,并推出了Socialite-Llama——一个开源的、指令调优的Llama模型。在20个社会科学任务组成的测试集上,Socialite-Llama相较于Llama提升了性能,并且在大多数任务上达到或超越了现有最先进的多任务微调模型的性能。此外,与Llama相比,Socialite-Llama在6个相关社会任务中的5个上也带来了改进,表明指令调优可以带来泛化的社会理解能力。包括我们的代码、模型和数据集在内的所有资源均可通过bit.ly/socialitellama获取。

英文摘要:

Social science NLP tasks, such as emotion or humor detection, are required to capture the semantics along with the implicit pragmatics from text, often with limited amounts of training data. Instruction tuning has been shown to improve the many capabilities of large language models (LLMs) such as commonsense reasoning, reading comprehension, and computer programming. However, little is known about the effectiveness of instruction tuning on the social domain where implicit pragmatic cues are often needed to be captured. We explore the use of instruction tuning for social science NLP tasks and introduce Socialite-Llama -- an open-source, instruction-tuned Llama. On a suite of 20 social science tasks, Socialite-Llama improves upon the performance of Llama as well as matches or improves upon the performance of a state-of-the-art, multi-task finetuned model on a majority of them. Further, Socialite-Llama also leads to improvement on 5 out of 6 related social tasks as compared to Llama, suggesting instruction tuning can lead to generalized social understanding. All resources including our code, model and dataset can be found through bit.ly/socialitellama.

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。

↑