中文
相关论文

相关论文: TAIA: Large Language Models are Out-of-Distributio…

200 篇论文

Large Language Models (LLMs), being generic task solvers, are versatile. However, despite the vast amount of data they are trained on, there are speculations about their adaptation capabilities to a new domain. Additionally, the simple…

计算与语言 · 计算机科学 2025-09-03 Anum Afzal , Mehul Kumawat , Florian Matthes

The advent of transformer-based architectures and large language models (LLMs) have significantly advanced the performance of natural language processing (NLP) models. Since these LLMs are trained on huge corpuses of data from the web and…

计算与语言 · 计算机科学 2024-08-29 Arkadeep Baksi , Rahul Singh , Tarun Joshi

Recently, Large Language Models (LLMs) have garnered increasing attention in the field of natural language processing, revolutionizing numerous downstream tasks with powerful reasoning and generation abilities. For example, In-Context…

计算与语言 · 计算机科学 2024-12-04 Changzhi Zhou , Dandan Song , Yuhang Tian , Zhijing Wu , Hao Wang , Xinyu Zhang , Jun Yang , Ziyi Yang , Shuhao Zhang

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…

计算与语言 · 计算机科学 2023-12-19 Bingchen Zhao , Haoqin Tu , Chen Wei , Jieru Mei , Cihang Xie

Driven by recent advances in artificial intelligence (AI), a growing literature has demonstrated the potential for using large language models (LLMs) as scalable surrogates to generate human-like responses in many business applications. Two…

机器学习 · 计算机科学 2025-12-30 Lei Wang , Zikun Ye , Jinglong Zhao

Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent studies demonstrate that open-sourced smaller foundational…

计算与语言 · 计算机科学 2023-10-10 Yue Zhang , Leyang Cui , Deng Cai , Xinting Huang , Tao Fang , Wei Bi

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased…

As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in…

计算与语言 · 计算机科学 2024-11-01 Nunzio Lore , Sepehr Ilami , Babak Heydari

Large Language Models are expressive tools that enable complex tasks of text understanding within Computational Social Science. Their versatility, while beneficial, poses a barrier for establishing standardized best practices within the…

计算机与社会 · 计算机科学 2024-08-05 Anders Giovanni Møller , Luca Maria Aiello

Large Language Models (LLMs) excel in general tasks, but adapting them to specialized domains relies on high-quality supervised fine-tuning (SFT) data. Although existing methods can identify subsets of high-quality data and reduce training…

计算与语言 · 计算机科学 2025-10-17 Zhaoyang Shang , Sibo Wei , Jianbin Guo , Rui Zhou , Lifeng Dong , Yin Luo

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

计算与语言 · 计算机科学 2022-07-11 Zejiang Hou , Julian Salazar , George Polovets

Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like…

机器学习 · 计算机科学 2025-07-28 Davor Vukadin , Marin Šilić , Goran Delač

Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user…

Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding…

机器学习 · 计算机科学 2023-12-29 Aditi Jha , Sam Havens , Jeremy Dohmann , Alex Trott , Jacob Portes

Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of…

计算与语言 · 计算机科学 2024-11-04 Yulong Wang , Chang Zuo , Yin Xuan , Hong Li , Ni Wei

Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about which mode yields greater language proficiency and whether they differ in their inductive…

In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code…

计算与语言 · 计算机科学 2023-08-03 Zhiqiang Yuan , Junwei Liu , Qiancheng Zi , Mingwei Liu , Xin Peng , Yiling Lou

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…

计算与语言 · 计算机科学 2024-04-16 Jiaxin Guo , Hao Yang , Zongyao Li , Daimeng Wei , Hengchao Shang , Xiaoyu Chen

Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…

计算与语言 · 计算机科学 2024-06-05 Bowen Zhao , Hannaneh Hajishirzi , Qingqing Cao

Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream…

软件工程 · 计算机科学 2024-01-05 Martin Weyssow , Xin Zhou , Kisub Kim , David Lo , Houari Sahraoui