English
Related papers

Related papers: What Makes Good Data for Alignment? A Comprehensiv…

200 papers

Instruction tuning of open-source large language models (LLMs) like LLaMA, using direct outputs from more powerful LLMs such as Instruct-GPT and GPT-4, has proven to be a cost-effective way to align model behaviors with human preferences.…

Computation and Language · Computer Science 2023-10-23 Haoran Li , Yiran Liu , Xingxing Zhang , Wei Lu , Furu Wei

Recent advancements in instruction tuning for large language models (LLMs) suggest that a small, high-quality dataset can significantly equip LLMs with instruction-following capabilities, outperforming large datasets often burdened by…

Machine Learning · Computer Science 2025-05-20 Jia Zhang , Chen-Xi Zhang , Yao Liu , Yi-Xuan Jin , Xiao-Wen Yang , Bo Zheng , Yi Liu , Lan-Zhe Guo

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

Computation and Language · Computer Science 2025-10-23 Zinan Tang , Xin Gao , Qizhi Pei , Zhuoshi Pan , Mengzhang Cai , Jiang Wu , Conghui He , Lijun Wu

Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs). While coding data is known to boost LLM reasoning abilities during pretraining, its role in activating internal…

Artificial Intelligence · Computer Science 2024-12-13 Xinlu Zhang , Zhiyu Zoey Chen , Xi Ye , Xianjun Yang , Lichang Chen , William Yang Wang , Linda Ruth Petzold

Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models (LLMs). While numerous studies have examined the impact of factors such as data volume and model size on English models, the scaling…

Computation and Language · Computer Science 2025-03-04 Chiyu Song , Zhanchao Zhou , Jianhao Yan , Yuejiao Fei , Zhenzhong Lan , Yue Zhang

Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or random magnitudes throughout the training process. While this…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Suorong Yang , Peijia Li , Xin Xiong , Furao Shen , Jian Zhao

Prompt tuning (PT) is an effective approach to adapting pre-trained language models to downstream tasks. Without a good initialization, prompt tuning doesn't perform well under few-shot settings. So pre-trained prompt tuning (PPT) is…

Computation and Language · Computer Science 2022-05-26 Yukun Huang , Kun Qian , Zhou Yu

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

Computation and Language · Computer Science 2025-05-27 Mahdi Nikdan , Vincent Cohen-Addad , Dan Alistarh , Vahab Mirrokni

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential.…

Computation and Language · Computer Science 2024-10-21 Mozhi Zhang , Pengyu Wang , Chenkun Tan , Mianqiu Huang , Dong Zhang , Yaqian Zhou , Xipeng Qiu

Aligned instruction following models can better fulfill user requests than their unaligned counterparts. However, it has been shown that there is a length bias in evaluation of such models, and that training algorithms tend to exploit this…

Computation and Language · Computer Science 2024-06-26 Weizhe Yuan , Ilia Kulikov , Ping Yu , Kyunghyun Cho , Sainbayar Sukhbaatar , Jason Weston , Jing Xu

Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically…

Computation and Language · Computer Science 2024-02-01 Pinzhen Chen , Shaoxiong Ji , Nikolay Bogoychev , Andrey Kutuzov , Barry Haddow , Kenneth Heafield

While large-scale training data is fundamental for developing capable large language models (LLMs), strategically selecting high-quality data has emerged as a critical approach to enhance training efficiency and reduce computational costs.…

Machine Learning · Computer Science 2025-07-23 Yang Yu , Kai Han , Hang Zhou , Yehui Tang , Kaiqi Huang , Yunhe Wang , Dacheng Tao

The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's…

Computation and Language · Computer Science 2023-03-28 Yunjie Ji , Yong Deng , Yan Gong , Yiping Peng , Qiang Niu , Lei Zhang , Baochang Ma , Xiangang Li

Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining from scratch is computationally infeasible. Fine-tuning…

Artificial Intelligence · Computer Science 2025-10-23 Xiao Han , Zimo Zhao , Wanyu Wang , Maolin Wang , Zitao Liu , Yi Chang , Xiangyu Zhao

Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yuan Liu , Le Tian , Xiao Zhou , Jie Zhou

General-purpose large language models (LLMs) are increasingly deployed in verticals such as telecommunications, where adaptation is hindered by scarce, low-information-density corpora and tight mobile/edge constraints. We propose Data…

Machine Learning · Computer Science 2025-11-11 Zhicheng Zhou , Jing Li , Suming Qiu , Junjie Huang , Linyuan Qiu , Zhijie Sun

High-quality supervised fine-tuning (SFT) data are crucial for eliciting strong capabilities from pretrained large language models (LLMs). Typically, instructions are paired with multiple responses sampled from other LLMs, which are often…

Computation and Language · Computer Science 2026-01-13 Dylan Zhang , Qirun Dai , Hao Peng

Large multimodal models still struggle with text-rich images because of inadequate training data. Self-Instruct provides an annotation-free way for generating instruction data, but its quality is poor, as multimodal alignment remains a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Shijie Zhou , Ruiyi Zhang , Yufan Zhou , Changyou Chen

Pretraining data of large language models composes multiple domains (e.g., web texts, academic papers, codes), whose mixture proportions crucially impact the competence of outcome models. While existing endeavors rely on heuristics or…

Computation and Language · Computer Science 2025-03-21 Jiasheng Ye , Peiju Liu , Tianxiang Sun , Jun Zhan , Yunhua Zhou , Xipeng Qiu

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

Machine Learning · Computer Science 2024-08-08 Shawn Im , Yixuan Li