中文
相关论文

相关论文: Exploring the Benefits of Training Expert Language…

200 篇论文

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

计算与语言 · 计算机科学 2024-10-29 Zheng Zhao , Yftah Ziser , Shay B. Cohen

While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their…

计算与语言 · 计算机科学 2024-03-15 Haoran Yang , Yumeng Zhang , Jiaqi Xu , Hongyuan Lu , Pheng Ann Heng , Wai Lam

Multi-task learning (MTL), instruction tuning, and prompting have recently been shown to improve the generalizability of large language models to new tasks. However, the benefits of such methods are less well-documented in smaller language…

计算与语言 · 计算机科学 2022-10-11 Alon Albalak , Akshat Shrivastava , Chinnadhurai Sankar , Adithya Sagar , Mike Ross

The potential of large language models (LLMs) to simultaneously perform a wide range of natural language processing (NLP) tasks has been the subject of extensive research. Although instruction tuning has proven to be a data-efficient method…

计算与语言 · 计算机科学 2023-10-25 Chufan Shi , Yixuan Su , Cheng Yang , Yujiu Yang , Deng Cai

The application of large language models (LLMs) in domain-specific contexts, including finance, has expanded rapidly. Domain-specific LLMs are typically evaluated based on their performance in various downstream tasks relevant to the…

人工智能 · 计算机科学 2024-12-06 Meni Brief , Oded Ovadia , Gil Shenderovitz , Noga Ben Yoash , Rachel Lemberg , Eitam Sheetrit

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), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, even state-of-the-art models struggle in certain cases,…

计算与语言 · 计算机科学 2025-01-16 Irina Bigoulaeva , Harish Tayyar Madabushi , Iryna Gurevych

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

Pretraining NLP models with variants of Masked Language Model (MLM) objectives has recently led to a significant improvements on many tasks. This paper examines the benefits of pretrained models as a function of the number of training…

计算与语言 · 计算机科学 2020-06-17 Sinong Wang , Madian Khabsa , Hao Ma

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a…

计算与语言 · 计算机科学 2024-05-22 Uri Shaham , Jonathan Herzig , Roee Aharoni , Idan Szpektor , Reut Tsarfaty , Matan Eyal

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1)…

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

How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families.…

人工智能 · 计算机科学 2026-04-22 Zhen Zhu , Yiming Gong , Yao Xiao , Yaoyao Liu , Derek Hoiem

Large language models have recently surpassed specialized systems on code generation, yet their effectiveness on other code-analysis tasks remains less clear. At the same time, multi-task learning offers a way to unify diverse objectives…

软件工程 · 计算机科学 2026-03-12 Amal Akli , Maxime Cordy , Mike Papadakis , Yves Le Traon

Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the…

人工智能 · 计算机科学 2023-05-17 Hao Chen , Yiming Zhang , Qi Zhang , Hantao Yang , Xiaomeng Hu , Xuetao Ma , Yifan Yanggong , Junbo Zhao

This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially…

计算与语言 · 计算机科学 2022-02-10 Jason Wei , Maarten Bosma , Vincent Y. Zhao , Kelvin Guu , Adams Wei Yu , Brian Lester , Nan Du , Andrew M. Dai , Quoc V. Le

While large language models (LLMs) often adopt finetuning to unlock their capabilities for downstream applications, our understanding on the inductive biases (especially the scaling properties) of different finetuning methods is still…

计算与语言 · 计算机科学 2024-02-28 Biao Zhang , Zhongtao Liu , Colin Cherry , Orhan Firat

Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…

计算与语言 · 计算机科学 2024-06-19 Shimao Zhang , Changjiang Gao , Wenhao Zhu , Jiajun Chen , Xin Huang , Xue Han , Junlan Feng , Chao Deng , Shujian Huang

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

计算与语言 · 计算机科学 2023-11-29 Utsav Garg , Erhan Bas

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

‹ 上一页 1 2 3 10 下一页 ›