中文
相关论文

相关论文: Take the essence and discard the dross: A Rethinki…

200 篇论文

Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than…

计算与语言 · 计算机科学 2025-08-27 Bolin Zhang , Jiahao Wang , Qianlong Du , Jiajun Zhang , Zhiying Tu , Dianhui Chu

Fine-tuning large language models (LLMs) with limited data poses a practical challenge in low-resource languages, specialized domains, and constrained deployment settings. While pre-trained LLMs provide strong foundations, effective…

计算与语言 · 计算机科学 2025-10-29 Marton Szep , Daniel Rueckert , Rüdiger von Eisenhart-Rothe , Florian Hinterwimmer

Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…

计算与语言 · 计算机科学 2025-03-06 Boris Nazarov , Darya Frolova , Yackov Lubarsky , Alexei Gaissinski , Pavel Kisilev

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

机器学习 · 计算机科学 2025-10-01 Animesh Jha , Harshit Gupta , Ananjan Nandi

Large language models (LLMs) alignment aims to ensure that the behavior of LLMs meets human preferences. While collecting data from multiple fine-grained, aspect-specific preferences becomes more and more feasible, existing alignment…

机器学习 · 计算机科学 2026-03-03 Jia Zhang , Yao Liu , Chen-Xi Zhang , Yi Liu , Yi-Xuan Jin , Lan-Zhe Guo , Yu-Feng Li

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that…

计算与语言 · 计算机科学 2024-12-10 Tingyu Xia , Bowen Yu , Kai Dang , An Yang , Yuan Wu , Yuan Tian , Yi Chang , Junyang Lin

This work focuses on leveraging and selecting from vast, unlabeled, open data to pre-fine-tune a pre-trained language model. The goal is to minimize the need for costly domain-specific data for subsequent fine-tuning while achieving desired…

Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is…

计算与语言 · 计算机科学 2025-09-05 Wei Huang , Huang Wei , Yinggui Wang

Finetuning large language models on instruction data is crucial for enhancing pre-trained knowledge and improving instruction-following capabilities. As instruction datasets proliferate, selecting optimal data for effective training becomes…

计算与语言 · 计算机科学 2024-09-18 Simon Yu , Liangyu Chen , Sara Ahmadian , Marzieh Fadaee

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data…

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and…

计算机视觉与模式识别 · 计算机科学 2024-12-31 Yulei Qin , Yuncheng Yang , Pengcheng Guo , Gang Li , Hang Shao , Yuchen Shi , Zihan Xu , Yun Gu , Ke Li , Xing Sun

This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel…

计算与语言 · 计算机科学 2024-07-22 Michael Oliver , Guan Wang

Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…

计算与语言 · 计算机科学 2025-10-31 Zhenqing Ling , Daoyuan Chen , Liuyi Yao , Qianli Shen , Yaliang Li , Ying Shen

Recent advances in large language models (LLMs) have provided new opportunities for decision-making, particularly in the task of automated feature selection. In this paper, we first comprehensively evaluate LLM-based feature selection…

机器学习 · 计算机科学 2025-12-12 Jianhao Li , Xianchao Xiu

The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLMs within search routines to iteratively generate and refine candidate algorithms. However, most…

机器学习 · 计算机科学 2026-05-20 Fei Liu , Rui Zhang , Xi Lin , Zhichao Lu , Qingfu Zhang

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

计算与语言 · 计算机科学 2025-03-21 Ishika Agarwal , Krishnateja Killamsetty , Lucian Popa , Marina Danilevksy

We propose a refined approach to efficiently fine-tune large language models (LLMs) on specific domains like the mathematical domain by employing a budgeted subset selection method. Our approach combines utility and diversity metrics to…

机器学习 · 计算机科学 2025-05-06 Madhav Kotecha , Vijendra Kumar Vaishya , Smita Gautam , Suraj Racha

Large Language Models (LLMs) have become a milestone in the field of artificial intelligence and natural language processing. However, their large-scale deployment remains constrained by the need for significant computational resources.…

计算与语言 · 计算机科学 2025-08-07 Julián Camilo Velandia Gutiérrez

Instruction tuning has become the de facto method to equip large language models (LLMs) with the ability of following user instructions. Usually, hundreds of thousands or millions of instruction-following pairs are employed to fine-tune the…

计算与语言 · 计算机科学 2023-11-28 Qianlong Du , Chengqing Zong , Jiajun Zhang

The rapid advancement of Large Language Models (LLMs) has significantly influenced various domains, leveraging their exceptional few-shot and zero-shot learning capabilities. In this work, we aim to explore and understand the LLMs-based…

人工智能 · 计算机科学 2024-10-24 Dawei Li , Zhen Tan , Huan Liu
‹ 上一页 1 2 3 10 下一页 ›